The document discusses using game theory and Shapley values to provide model-agnostic explanations for individual predictions from machine learning models. It introduces the concept of using an interpretable approximation function gx to explain the output f(x) of a complex model. It outlines two natural axioms - efficiency and monotonicity - that an explanation should satisfy. It then shows that under these axioms, Shapley values are the unique solution, forming the basis of the SHAP (Shapley Additive Explanations) method. The document argues this provides a unified framework for model-agnostic interpretability that connects and improves various existing explanation techniques.
Unified Approach to Interpret Machine Learning Model: SHAP + LIMEDatabricks
For companies that solve real-world problems and generate revenue from the data science products, being able to understand why a model makes a certain prediction can be as crucial as achieving high prediction accuracy in many applications. However, as data scientists pursuing higher accuracy by implementing complex algorithms such as ensemble or deep learning models, the algorithm itself becomes a blackbox and it creates the trade-off between accuracy and interpretability of a model’s output.
To address this problem, a unified framework SHAP (SHapley Additive exPlanations) was developed to help users interpret the predictions of complex models. In this session, we will talk about how to apply SHAP to various modeling approaches (GLM, XGBoost, CNN) to explain how each feature contributes and extract intuitive insights from a particular prediction. This talk is intended to introduce the concept of general purpose model explainer, as well as help practitioners understand SHAP and its applications.
It's a well-known fact that the best explanation of a simple model is the model itself. But often we use complex models, such as ensemble methods or deep networks, so we cannot use the original model as its own best explanation because it is not easy to understand.
In the context of this topic, we will discuss how methods for interpreting model predictions work and will try to understand practical value of these methods.
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding why certains predictions are made are very important in assessing trust, which is very important if one plans to take action based on a prediction. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one. If the user does not trust the model they will never use it .
Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...Sri Ambati
Abstract:
Explainability in the age of the EU GDPR is becoming an increasingly pertinent consideration for Machine Learning. At QuantumBlack, we address the traditional Accuracy vs. Interpretability trade-off, by leveraging modern XAI techniques such as LIME and SHAP, to enable individualised explanations without necessary limiting the utility and performance of the otherwise ‘black-box’ models. The talk focuses on Shapley additive explanations (Lundberg et al. 2017) that integrate Shapley values from the Game Theory for consistent and locally accurate explanations; provides illustrative examples and touches upon the wider XAI theory.
Bio:
Dr Torgyn Shaikhina is a Data Scientist at QuantumBlack, STEM Ambassador, and the founder of the Next Generation Programmers outreach initiative. Her background is in decision support systems for Healthcare and Biomedical Engineering with a focus on Machine Learning with limited information.
Slide for Arithmer Seminar given by Dr. Daisuke Sato (Arithmer) at Arithmer inc.
The topic is on "explainable AI".
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
This was presented at the London Artificial Intelligence & Deep Learning Meetup.
https://www.meetup.com/London-Artificial-Intelligence-Deep-Learning/events/245251725/
Enjoy the recording: https://youtu.be/CY3t11vuuOM.
- - -
Kasia discussed complexities of interpreting black-box algorithms and how these may affect some industries. She presented the most popular methods of interpreting Machine Learning classifiers, for example, feature importance or partial dependence plots and Bayesian networks. Finally, she introduced Local Interpretable Model-Agnostic Explanations (LIME) framework for explaining predictions of black-box learners – including text- and image-based models - using breast cancer data as a specific case scenario.
Kasia Kulma is a Data Scientist at Aviva with a soft spot for R. She obtained a PhD (Uppsala University, Sweden) in evolutionary biology in 2013 and has been working on all things data ever since. For example, she has built recommender systems, customer segmentations, predictive models and now she is leading an NLP project at the UK’s leading insurer. In spare time she tries to relax by hiking & camping, but if that doesn’t work ;) she co-organizes R-Ladies meetups and writes a data science blog R-tastic (https://kkulma.github.io/).
https://www.linkedin.com/in/kasia-kulma-phd-7695b923/
Introductory presentation to Explainable AI, defending its main motivations and importance. We describe briefly the main techniques available in March 2020 and share many references to allow the reader to continue his/her studies.
Unified Approach to Interpret Machine Learning Model: SHAP + LIMEDatabricks
For companies that solve real-world problems and generate revenue from the data science products, being able to understand why a model makes a certain prediction can be as crucial as achieving high prediction accuracy in many applications. However, as data scientists pursuing higher accuracy by implementing complex algorithms such as ensemble or deep learning models, the algorithm itself becomes a blackbox and it creates the trade-off between accuracy and interpretability of a model’s output.
To address this problem, a unified framework SHAP (SHapley Additive exPlanations) was developed to help users interpret the predictions of complex models. In this session, we will talk about how to apply SHAP to various modeling approaches (GLM, XGBoost, CNN) to explain how each feature contributes and extract intuitive insights from a particular prediction. This talk is intended to introduce the concept of general purpose model explainer, as well as help practitioners understand SHAP and its applications.
It's a well-known fact that the best explanation of a simple model is the model itself. But often we use complex models, such as ensemble methods or deep networks, so we cannot use the original model as its own best explanation because it is not easy to understand.
In the context of this topic, we will discuss how methods for interpreting model predictions work and will try to understand practical value of these methods.
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding why certains predictions are made are very important in assessing trust, which is very important if one plans to take action based on a prediction. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one. If the user does not trust the model they will never use it .
Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...Sri Ambati
Abstract:
Explainability in the age of the EU GDPR is becoming an increasingly pertinent consideration for Machine Learning. At QuantumBlack, we address the traditional Accuracy vs. Interpretability trade-off, by leveraging modern XAI techniques such as LIME and SHAP, to enable individualised explanations without necessary limiting the utility and performance of the otherwise ‘black-box’ models. The talk focuses on Shapley additive explanations (Lundberg et al. 2017) that integrate Shapley values from the Game Theory for consistent and locally accurate explanations; provides illustrative examples and touches upon the wider XAI theory.
Bio:
Dr Torgyn Shaikhina is a Data Scientist at QuantumBlack, STEM Ambassador, and the founder of the Next Generation Programmers outreach initiative. Her background is in decision support systems for Healthcare and Biomedical Engineering with a focus on Machine Learning with limited information.
Slide for Arithmer Seminar given by Dr. Daisuke Sato (Arithmer) at Arithmer inc.
The topic is on "explainable AI".
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
This was presented at the London Artificial Intelligence & Deep Learning Meetup.
https://www.meetup.com/London-Artificial-Intelligence-Deep-Learning/events/245251725/
Enjoy the recording: https://youtu.be/CY3t11vuuOM.
- - -
Kasia discussed complexities of interpreting black-box algorithms and how these may affect some industries. She presented the most popular methods of interpreting Machine Learning classifiers, for example, feature importance or partial dependence plots and Bayesian networks. Finally, she introduced Local Interpretable Model-Agnostic Explanations (LIME) framework for explaining predictions of black-box learners – including text- and image-based models - using breast cancer data as a specific case scenario.
Kasia Kulma is a Data Scientist at Aviva with a soft spot for R. She obtained a PhD (Uppsala University, Sweden) in evolutionary biology in 2013 and has been working on all things data ever since. For example, she has built recommender systems, customer segmentations, predictive models and now she is leading an NLP project at the UK’s leading insurer. In spare time she tries to relax by hiking & camping, but if that doesn’t work ;) she co-organizes R-Ladies meetups and writes a data science blog R-tastic (https://kkulma.github.io/).
https://www.linkedin.com/in/kasia-kulma-phd-7695b923/
Introductory presentation to Explainable AI, defending its main motivations and importance. We describe briefly the main techniques available in March 2020 and share many references to allow the reader to continue his/her studies.
Machine Learning and computing power have made huge improvements in the last decade. It’s now possible to unlock complex problems in multidimensional space with ensemble, brute force algorithms or deep neural networks, with performances that were unthinkable a few years ago. However the use of black box models is still frown upon in a business setting. In fact the decision functions of those models are often impossible to interpret for humans, can be biased or just based on absurd assumption. What if your risk model denies loans to people on ethnic ground? SHAP comes as an innovative framework to obtain local explanations for the output of a model, making the black box much more transparent.
Interpretierbarkeit von ML-Modellen hat die Zielsetzung, die Ursachen einer Prognose offenzulegen und eine daraus abgeleitete Entscheidung für einen Menschen nachvollziehbar zu erklären. Durch die Nachvollziehbarkeit von Prognosen lässt sich beispielsweise sicherstellen, dass deren Herleitung konsistent zum Domänenwissen eines Experten ist. Auch ein unfairer Bias lässt sich durch die Erklärung aussagekräftiger Beispiele identifizieren.
Prognosemodelle lassen sich grob in intrinsisch interpretierbare Modelle und nicht-interpretierbare (auch Blackbox-) Modelle unterscheiden. Intrinsisch interpretierbare Modelle sind dafür bekannt, dass sie für einen Menschen leicht nachvollziehbar sind. Ein typisches Beispiel für ein solches Modell ist der Entscheidungsbaum, dessen regelbasierter Entscheidungsprozess intuitiv und leicht zugänglich ist. Im Gegensatz dazu gelten Neuronale Netze als Blackbox-Modelle, deren Prognosen durch die komplexe Netzstruktur schwer nachvollziehbar sind.
In diesem Talk erläuterte Marcel Spitzer das Konzept von Interpretierbarkeit im Kontext von Machine Learning und stellte gängige Verfahren zur Interpretation von Modellen vor. Besonderen Fokus legte er dabei auf modellunabhängige Verfahren, die sich auch auf prognosestarke Blackbox-Modelle anwenden lassen.
Event: M3 Minds Mastering Machines
Speaker: Marcel Spitzer
Blog-Artikel: https://www.inovex.de/blog/machine-learning-interpretability/
Mehr Tech-Vorträge: inovex.de/vortraege
Mehr Tech-Artikel: inovex.de/blog
An Introduction to XAI! Towards Trusting Your ML Models!Mansour Saffar
Machine learning (ML) is currently disrupting almost every industry and is being used as the core component in many systems. The decisions made by these systems may have a great impact on society and specific individuals and thus the decision-making process has to be clear and explainable so humans can trust it. Explainable AI (XAI) is a rather new field in ML in which researchers try to develop models that are able to explain the decision-making process behind ML models. In this talk, we'll learn about the fundamentals of XAI and discuss why we need to start to integrate XAI with our ML models!
Presented in Edmonton DataScience Meetup on October 2nd, 2019. Learn more: https://youtu.be/gEkPXOsDt_w
Artificial Intelligence is increasingly playing an integral role in determining our day-to-day experiences. Moreover, with proliferation of AI based solutions in areas such as hiring, lending, criminal justice, healthcare, and education, the resulting personal and professional implications of AI are far-reaching. The dominant role played by AI models in these domains has led to a growing concern regarding potential bias in these models, and a demand for model transparency and interpretability. In addition, model explainability is a prerequisite for building trust and adoption of AI systems in high stakes domains requiring reliability and safety such as healthcare and automated transportation, as well as critical industrial applications with significant economic implications such as predictive maintenance, exploration of natural resources, and climate change modeling.
As a consequence, AI researchers and practitioners have focused their attention on explainable AI to help them better trust and understand models at scale. The challenges for the research community include (i) defining model explainability, (ii) formulating explainability tasks for understanding model behavior and developing solutions for these tasks, and finally (iii) designing measures for evaluating the performance of models in explainability tasks.
In this tutorial, we will first motivate the need for model interpretability and explainability in AI from societal, legal, customer/end-user, and model developer perspectives. [Note: Due to time constraints, we will not focus on techniques/tools for providing explainability as part of AI/ML systems.] Then, we will focus on the real-world application of explainability techniques in industry, wherein we present practical challenges / implications for using explainability techniques effectively and lessons learned from deploying explainable models for several web-scale machine learning and data mining applications. We will present case studies across different companies, spanning application domains such as search and recommendation systems, sales, lending, and fraud detection. Finally, based on our experiences in industry, we will identify open problems and research directions for the research community.
Understanding how high powered ML models arrive at their predictions is an important aspect of Machine Learning, and SHAP is a powerful tool that enables practitioners to understand how different features combine to help a model arrive at a prediction.
This slidedeck is from a presentation given at pydata global on the theoretical foundations of SHAP as well as how to use its library. Link to the presentation can be found here: https://pydata.org/global2021/schedule/presentation/3/behind-the-black-box-how-to-understand-any-ml-model-using-shap/
[Video recording available at https://www.youtube.com/playlist?list=PLewjn-vrZ7d3x0M4Uu_57oaJPRXkiS221]
Artificial Intelligence is increasingly playing an integral role in determining our day-to-day experiences. Moreover, with proliferation of AI based solutions in areas such as hiring, lending, criminal justice, healthcare, and education, the resulting personal and professional implications of AI are far-reaching. The dominant role played by AI models in these domains has led to a growing concern regarding potential bias in these models, and a demand for model transparency and interpretability. In addition, model explainability is a prerequisite for building trust and adoption of AI systems in high stakes domains requiring reliability and safety such as healthcare and automated transportation, and critical industrial applications with significant economic implications such as predictive maintenance, exploration of natural resources, and climate change modeling.
As a consequence, AI researchers and practitioners have focused their attention on explainable AI to help them better trust and understand models at scale. The challenges for the research community include (i) defining model explainability, (ii) formulating explainability tasks for understanding model behavior and developing solutions for these tasks, and finally (iii) designing measures for evaluating the performance of models in explainability tasks.
In this tutorial, we present an overview of model interpretability and explainability in AI, key regulations / laws, and techniques / tools for providing explainability as part of AI/ML systems. Then, we focus on the application of explainability techniques in industry, wherein we present practical challenges / guidelines for effectively using explainability techniques and lessons learned from deploying explainable models for several web-scale machine learning and data mining applications. We present case studies across different companies, spanning application domains such as search & recommendation systems, hiring, sales, and lending. Finally, based on our experiences in industry, we identify open problems and research directions for the data mining / machine learning community.
Explainable AI makes the algorithms to be transparent where they interpret, visualize, explain and integrate for fair, secure and trustworthy AI applications.
Scott Lundberg, Microsoft Research - Explainable Machine Learning with Shaple...Sri Ambati
This session was recorded in NYC on October 22nd, 2019 and can be viewed here: https://youtu.be/ngOBhhINWb8
Explainable Machine Learning with Shapley Values
Shapley values are popular approach for explaining predictions made by complex machine learning models. In this talk I will discuss what problems Shapley values solve, an intuitive presentation of what they mean, and examples of how they can be used through the ‘shap’ python package.
Bio: I am a senior researcher at Microsoft Research. Before joining Microsoft, I did my Ph.D. studies at the Paul G. Allen School of Computer Science & Engineering of the University of Washington working with Su-In Lee. My work focuses on explainable artificial intelligence and its application to problems in medicine and healthcare. This has led to the development of broadly applicable methods and tools for interpreting complex machine learning models that are now used in banking, logistics, sports, manufacturing, cloud services, economics, and many other areas.
The importance of model fairness and interpretability in AI systemsFrancesca Lazzeri, PhD
Machine learning model fairness and interpretability are critical for data scientists, researchers and developers to explain their models and understand the value and accuracy of their findings. Interpretability is also important to debug machine learning models and make informed decisions about how to improve them.
In this session, Francesca will go over a few methods and tools that enable you to "unpack” machine learning models, gain insights into how and why they produce specific results, assess your AI systems fairness and mitigate any observed fairness issues.
Using open-source fairness and interpretability packages, attendees will learn how to:
- Explain model prediction by generating feature importance values for the entire model and/or individual data points.
- Achieve model interpretability on real-world datasets at scale, during training and inference.
- Use an interactive visualization dashboard to discover patterns in data and explanations at training time.
- Leverage additional interactive visualizations to assess which groups of users might be negatively impacted by a model and compare multiple models in terms of their fairness and performance.
Explainable AI - making ML and DL models more interpretableAditya Bhattacharya
Abstract –
Although industries have started to adopt AI and Machine Learning in almost every sector to solve complex business problems, but are these models always trustworthy? Machine Learning models are not any oracle but rather are scientific methods and mathematical models which best describes the data. But science is all about explaining complex natural phenomena in the simplest way possible! So, can we make ML and DL models more interpretable, so that any business user can understand these models and trust the results of these models?
In order to find out the answer, please join me in this session, in which I will take about concepts of Explainable AI and discuss its necessity and principles which help us demystify black-box AI models. I will be discussing about popular approaches like Feature Importance, Key Influencers, Decomposition trees used in classical Machine Learning interpretable. We will discuss about various techniques used for Deep Learning model interpretations like Saliency Maps, Grad-CAMs, Visual Attention Maps and finally go through more details about frameworks like LIME, SHAP, ELI5, SKATER, TCAV which helps us to make Machine Learning and Deep Learning models more interpretable, trustworthy and useful!
A Unified Approach to Interpreting Model Predictions (SHAP)Rama Irsheidat
A Unified Approach to Interpreting Model Predictions.
Scott M. Lundberg, Su-In Lee.
Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by complex models that even experts struggle to interpret, such as ensemble or deep learning models, creating a tension between accuracy and interpretability. In response, various methods have recently been proposed to help users interpret the predictions of complex models, but it is often unclear how these methods are related and when one method is preferable over another. To address this problem, we present a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations). SHAP assigns each feature an importance value for a particular prediction. Its novel components include: (1) the identification of a new class of additive feature importance measures, and (2) theoretical results showing there is a unique solution in this class with a set of desirable properties. The new class unifies six existing methods, notable because several recent methods in the class lack the proposed desirable properties. Based on insights from this unification, we present new methods that show improved computational performance and/or better consistency with human intuition than previous approaches.
Interpretable Machine Learning describes the process of revealing causes of predictions and explaining a derived decision in a way that is understandable to humans. The ability to understand the causes that lead to a certain prediction enables data scientists to ensure that the model is consistent to the domain knowledge of an expert. Furthermore, interpretability is critical to obtain trust in a model and to be able to tackle problems like unfair biases or discrimination against particular subgroups. This talk covers an introduction to the concept of interpretability and an overview of popular interpretability techniques.
Speaker: Marcel Spitzer, inovex
Event: Kaggle Munich Meetup, 20.11.2018
Mehr Tech-Vorträge: www.inovex.de/vortraege
Mehr Tech-Artikel: www.inovex.de/blog
Interpreting deep learning and machine learning models is not just another regulatory burden to be overcome. Scientists, physicians, researchers, and analyst that use these technologies for their important work have the right to trust and understand their models and the answers they generate. This talk is an overview of several techniques for interpreting deep learning and machine learning models and telling stories from their results.
Speaker: Patrick Hall is a Data Scientist and Product Engineer at H2O.ai. He’s also an Adjunct Professor at George Washington University for the Department of Decision Sciences. Prior to joining H2O, Patrick spent many years as a Senior Data Scientist SAS and has worked with many Fortune 500 companies on their data science and machine learning problems. https://www.linkedin.com/in/jpatrickhall
Explainable AI (XAI) is becoming Must-Have NFR for most AI enabled product or solution deployments. Keen to know viewpoints and collaboration opportunities.
https://github.com/telecombcn-dl/lectures-all/
These slides review techniques for interpreting the behavior of deep neural networks. The talk reviews basic techniques such as the display of filters and tensors, as well as more advanced ones that try to interpret which part of the input data is responsible for the predictions, or generate data that maximizes the activation of certain neurons.
Explainable Artificial Intelligence (XAI)
Presented at Lightning Talk session at ICACCI'18 on 20th September 208
An Explainable AI (XAI) or Transparent AI is an artificial intelligence (AI) whose actions can be easily understood by humans. It contrasts with the concept of the "black box" in machine learning, meaning the "interpretability" of the workings of complex algorithms, where even their designers cannot explain why the AI arrived at a specific decision.
https://en.wikipedia.org/wiki/Explainable_Artificial_Intelligence
Explainable AI: Building trustworthy AI models? Raheel Ahmad
Building trustworthy, transparent and unbiased machine learning models?
Get started with explainX that brings state-of-the-art explainability techniques under one roof accessible via one-line of code.
Learn the major modules within the explainX explainable AI and model interpretability framework.
These slides are taken from Raheel's presentation at the UnpackAI's forum on Data Ethics in AI.
This presentation talks about some of the outstanding methods for Interpreting the complex machine learning black box models. One of the ideas is to use interpretable simple models to explain predictions using sophisticated black box machine learning models.
Model Agnostic methods are proven to have some specific advantages over the Model Specific Methods of Interpretability. This work demonstrates some of such results.
Deep Learning: Introduction & Chapter 5 Machine Learning BasicsJason Tsai
Given lecture for Deep Learning 101 study group with Frank Wu on Dec. 9th, 2016.
Reference: https://www.deeplearningbook.org/
Initiated by Taiwan AI Group (https://www.facebook.com/groups/Taiwan.AI.Group/)
Machine Learning and computing power have made huge improvements in the last decade. It’s now possible to unlock complex problems in multidimensional space with ensemble, brute force algorithms or deep neural networks, with performances that were unthinkable a few years ago. However the use of black box models is still frown upon in a business setting. In fact the decision functions of those models are often impossible to interpret for humans, can be biased or just based on absurd assumption. What if your risk model denies loans to people on ethnic ground? SHAP comes as an innovative framework to obtain local explanations for the output of a model, making the black box much more transparent.
Interpretierbarkeit von ML-Modellen hat die Zielsetzung, die Ursachen einer Prognose offenzulegen und eine daraus abgeleitete Entscheidung für einen Menschen nachvollziehbar zu erklären. Durch die Nachvollziehbarkeit von Prognosen lässt sich beispielsweise sicherstellen, dass deren Herleitung konsistent zum Domänenwissen eines Experten ist. Auch ein unfairer Bias lässt sich durch die Erklärung aussagekräftiger Beispiele identifizieren.
Prognosemodelle lassen sich grob in intrinsisch interpretierbare Modelle und nicht-interpretierbare (auch Blackbox-) Modelle unterscheiden. Intrinsisch interpretierbare Modelle sind dafür bekannt, dass sie für einen Menschen leicht nachvollziehbar sind. Ein typisches Beispiel für ein solches Modell ist der Entscheidungsbaum, dessen regelbasierter Entscheidungsprozess intuitiv und leicht zugänglich ist. Im Gegensatz dazu gelten Neuronale Netze als Blackbox-Modelle, deren Prognosen durch die komplexe Netzstruktur schwer nachvollziehbar sind.
In diesem Talk erläuterte Marcel Spitzer das Konzept von Interpretierbarkeit im Kontext von Machine Learning und stellte gängige Verfahren zur Interpretation von Modellen vor. Besonderen Fokus legte er dabei auf modellunabhängige Verfahren, die sich auch auf prognosestarke Blackbox-Modelle anwenden lassen.
Event: M3 Minds Mastering Machines
Speaker: Marcel Spitzer
Blog-Artikel: https://www.inovex.de/blog/machine-learning-interpretability/
Mehr Tech-Vorträge: inovex.de/vortraege
Mehr Tech-Artikel: inovex.de/blog
An Introduction to XAI! Towards Trusting Your ML Models!Mansour Saffar
Machine learning (ML) is currently disrupting almost every industry and is being used as the core component in many systems. The decisions made by these systems may have a great impact on society and specific individuals and thus the decision-making process has to be clear and explainable so humans can trust it. Explainable AI (XAI) is a rather new field in ML in which researchers try to develop models that are able to explain the decision-making process behind ML models. In this talk, we'll learn about the fundamentals of XAI and discuss why we need to start to integrate XAI with our ML models!
Presented in Edmonton DataScience Meetup on October 2nd, 2019. Learn more: https://youtu.be/gEkPXOsDt_w
Artificial Intelligence is increasingly playing an integral role in determining our day-to-day experiences. Moreover, with proliferation of AI based solutions in areas such as hiring, lending, criminal justice, healthcare, and education, the resulting personal and professional implications of AI are far-reaching. The dominant role played by AI models in these domains has led to a growing concern regarding potential bias in these models, and a demand for model transparency and interpretability. In addition, model explainability is a prerequisite for building trust and adoption of AI systems in high stakes domains requiring reliability and safety such as healthcare and automated transportation, as well as critical industrial applications with significant economic implications such as predictive maintenance, exploration of natural resources, and climate change modeling.
As a consequence, AI researchers and practitioners have focused their attention on explainable AI to help them better trust and understand models at scale. The challenges for the research community include (i) defining model explainability, (ii) formulating explainability tasks for understanding model behavior and developing solutions for these tasks, and finally (iii) designing measures for evaluating the performance of models in explainability tasks.
In this tutorial, we will first motivate the need for model interpretability and explainability in AI from societal, legal, customer/end-user, and model developer perspectives. [Note: Due to time constraints, we will not focus on techniques/tools for providing explainability as part of AI/ML systems.] Then, we will focus on the real-world application of explainability techniques in industry, wherein we present practical challenges / implications for using explainability techniques effectively and lessons learned from deploying explainable models for several web-scale machine learning and data mining applications. We will present case studies across different companies, spanning application domains such as search and recommendation systems, sales, lending, and fraud detection. Finally, based on our experiences in industry, we will identify open problems and research directions for the research community.
Understanding how high powered ML models arrive at their predictions is an important aspect of Machine Learning, and SHAP is a powerful tool that enables practitioners to understand how different features combine to help a model arrive at a prediction.
This slidedeck is from a presentation given at pydata global on the theoretical foundations of SHAP as well as how to use its library. Link to the presentation can be found here: https://pydata.org/global2021/schedule/presentation/3/behind-the-black-box-how-to-understand-any-ml-model-using-shap/
[Video recording available at https://www.youtube.com/playlist?list=PLewjn-vrZ7d3x0M4Uu_57oaJPRXkiS221]
Artificial Intelligence is increasingly playing an integral role in determining our day-to-day experiences. Moreover, with proliferation of AI based solutions in areas such as hiring, lending, criminal justice, healthcare, and education, the resulting personal and professional implications of AI are far-reaching. The dominant role played by AI models in these domains has led to a growing concern regarding potential bias in these models, and a demand for model transparency and interpretability. In addition, model explainability is a prerequisite for building trust and adoption of AI systems in high stakes domains requiring reliability and safety such as healthcare and automated transportation, and critical industrial applications with significant economic implications such as predictive maintenance, exploration of natural resources, and climate change modeling.
As a consequence, AI researchers and practitioners have focused their attention on explainable AI to help them better trust and understand models at scale. The challenges for the research community include (i) defining model explainability, (ii) formulating explainability tasks for understanding model behavior and developing solutions for these tasks, and finally (iii) designing measures for evaluating the performance of models in explainability tasks.
In this tutorial, we present an overview of model interpretability and explainability in AI, key regulations / laws, and techniques / tools for providing explainability as part of AI/ML systems. Then, we focus on the application of explainability techniques in industry, wherein we present practical challenges / guidelines for effectively using explainability techniques and lessons learned from deploying explainable models for several web-scale machine learning and data mining applications. We present case studies across different companies, spanning application domains such as search & recommendation systems, hiring, sales, and lending. Finally, based on our experiences in industry, we identify open problems and research directions for the data mining / machine learning community.
Explainable AI makes the algorithms to be transparent where they interpret, visualize, explain and integrate for fair, secure and trustworthy AI applications.
Scott Lundberg, Microsoft Research - Explainable Machine Learning with Shaple...Sri Ambati
This session was recorded in NYC on October 22nd, 2019 and can be viewed here: https://youtu.be/ngOBhhINWb8
Explainable Machine Learning with Shapley Values
Shapley values are popular approach for explaining predictions made by complex machine learning models. In this talk I will discuss what problems Shapley values solve, an intuitive presentation of what they mean, and examples of how they can be used through the ‘shap’ python package.
Bio: I am a senior researcher at Microsoft Research. Before joining Microsoft, I did my Ph.D. studies at the Paul G. Allen School of Computer Science & Engineering of the University of Washington working with Su-In Lee. My work focuses on explainable artificial intelligence and its application to problems in medicine and healthcare. This has led to the development of broadly applicable methods and tools for interpreting complex machine learning models that are now used in banking, logistics, sports, manufacturing, cloud services, economics, and many other areas.
The importance of model fairness and interpretability in AI systemsFrancesca Lazzeri, PhD
Machine learning model fairness and interpretability are critical for data scientists, researchers and developers to explain their models and understand the value and accuracy of their findings. Interpretability is also important to debug machine learning models and make informed decisions about how to improve them.
In this session, Francesca will go over a few methods and tools that enable you to "unpack” machine learning models, gain insights into how and why they produce specific results, assess your AI systems fairness and mitigate any observed fairness issues.
Using open-source fairness and interpretability packages, attendees will learn how to:
- Explain model prediction by generating feature importance values for the entire model and/or individual data points.
- Achieve model interpretability on real-world datasets at scale, during training and inference.
- Use an interactive visualization dashboard to discover patterns in data and explanations at training time.
- Leverage additional interactive visualizations to assess which groups of users might be negatively impacted by a model and compare multiple models in terms of their fairness and performance.
Explainable AI - making ML and DL models more interpretableAditya Bhattacharya
Abstract –
Although industries have started to adopt AI and Machine Learning in almost every sector to solve complex business problems, but are these models always trustworthy? Machine Learning models are not any oracle but rather are scientific methods and mathematical models which best describes the data. But science is all about explaining complex natural phenomena in the simplest way possible! So, can we make ML and DL models more interpretable, so that any business user can understand these models and trust the results of these models?
In order to find out the answer, please join me in this session, in which I will take about concepts of Explainable AI and discuss its necessity and principles which help us demystify black-box AI models. I will be discussing about popular approaches like Feature Importance, Key Influencers, Decomposition trees used in classical Machine Learning interpretable. We will discuss about various techniques used for Deep Learning model interpretations like Saliency Maps, Grad-CAMs, Visual Attention Maps and finally go through more details about frameworks like LIME, SHAP, ELI5, SKATER, TCAV which helps us to make Machine Learning and Deep Learning models more interpretable, trustworthy and useful!
A Unified Approach to Interpreting Model Predictions (SHAP)Rama Irsheidat
A Unified Approach to Interpreting Model Predictions.
Scott M. Lundberg, Su-In Lee.
Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by complex models that even experts struggle to interpret, such as ensemble or deep learning models, creating a tension between accuracy and interpretability. In response, various methods have recently been proposed to help users interpret the predictions of complex models, but it is often unclear how these methods are related and when one method is preferable over another. To address this problem, we present a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations). SHAP assigns each feature an importance value for a particular prediction. Its novel components include: (1) the identification of a new class of additive feature importance measures, and (2) theoretical results showing there is a unique solution in this class with a set of desirable properties. The new class unifies six existing methods, notable because several recent methods in the class lack the proposed desirable properties. Based on insights from this unification, we present new methods that show improved computational performance and/or better consistency with human intuition than previous approaches.
Interpretable Machine Learning describes the process of revealing causes of predictions and explaining a derived decision in a way that is understandable to humans. The ability to understand the causes that lead to a certain prediction enables data scientists to ensure that the model is consistent to the domain knowledge of an expert. Furthermore, interpretability is critical to obtain trust in a model and to be able to tackle problems like unfair biases or discrimination against particular subgroups. This talk covers an introduction to the concept of interpretability and an overview of popular interpretability techniques.
Speaker: Marcel Spitzer, inovex
Event: Kaggle Munich Meetup, 20.11.2018
Mehr Tech-Vorträge: www.inovex.de/vortraege
Mehr Tech-Artikel: www.inovex.de/blog
Interpreting deep learning and machine learning models is not just another regulatory burden to be overcome. Scientists, physicians, researchers, and analyst that use these technologies for their important work have the right to trust and understand their models and the answers they generate. This talk is an overview of several techniques for interpreting deep learning and machine learning models and telling stories from their results.
Speaker: Patrick Hall is a Data Scientist and Product Engineer at H2O.ai. He’s also an Adjunct Professor at George Washington University for the Department of Decision Sciences. Prior to joining H2O, Patrick spent many years as a Senior Data Scientist SAS and has worked with many Fortune 500 companies on their data science and machine learning problems. https://www.linkedin.com/in/jpatrickhall
Explainable AI (XAI) is becoming Must-Have NFR for most AI enabled product or solution deployments. Keen to know viewpoints and collaboration opportunities.
https://github.com/telecombcn-dl/lectures-all/
These slides review techniques for interpreting the behavior of deep neural networks. The talk reviews basic techniques such as the display of filters and tensors, as well as more advanced ones that try to interpret which part of the input data is responsible for the predictions, or generate data that maximizes the activation of certain neurons.
Explainable Artificial Intelligence (XAI)
Presented at Lightning Talk session at ICACCI'18 on 20th September 208
An Explainable AI (XAI) or Transparent AI is an artificial intelligence (AI) whose actions can be easily understood by humans. It contrasts with the concept of the "black box" in machine learning, meaning the "interpretability" of the workings of complex algorithms, where even their designers cannot explain why the AI arrived at a specific decision.
https://en.wikipedia.org/wiki/Explainable_Artificial_Intelligence
Explainable AI: Building trustworthy AI models? Raheel Ahmad
Building trustworthy, transparent and unbiased machine learning models?
Get started with explainX that brings state-of-the-art explainability techniques under one roof accessible via one-line of code.
Learn the major modules within the explainX explainable AI and model interpretability framework.
These slides are taken from Raheel's presentation at the UnpackAI's forum on Data Ethics in AI.
This presentation talks about some of the outstanding methods for Interpreting the complex machine learning black box models. One of the ideas is to use interpretable simple models to explain predictions using sophisticated black box machine learning models.
Model Agnostic methods are proven to have some specific advantages over the Model Specific Methods of Interpretability. This work demonstrates some of such results.
Deep Learning: Introduction & Chapter 5 Machine Learning BasicsJason Tsai
Given lecture for Deep Learning 101 study group with Frank Wu on Dec. 9th, 2016.
Reference: https://www.deeplearningbook.org/
Initiated by Taiwan AI Group (https://www.facebook.com/groups/Taiwan.AI.Group/)
---TABLE OF CONTENT---
Introduction
Differences between crisp sets & Fuzzy sets
Operations on Fuzzy Sets
Properties
MF formulation and parameterization
Fuzzy rules and Fuzzy reasoning
Fuzzy interface systems
Introduction to genetic algorithm
Score Week 5 Correlation and RegressionCorrelation and Regres.docxkenjordan97598
Score: Week 5 Correlation and RegressionCorrelation and RegressionCorrelation and Regression
<1 point> 1. Create a correlation table for the variables in our data set. (Use analysis ToolPak or StatPlus:mac LE function Correlation.)Create a correlation table for the variables in our data set. (Use analysis ToolPak or StatPlus:mac LE function Correlation.)Create a correlation table for the variables in our data set. (Use analysis ToolPak or StatPlus:mac LE function Correlation.)Create a correlation table for the variables in our data set. (Use analysis ToolPak or StatPlus:mac LE function Correlation.)Create a correlation table for the variables in our data set. (Use analysis ToolPak or StatPlus:mac LE function Correlation.)Create a correlation table for the variables in our data set. (Use analysis ToolPak or StatPlus:mac LE function Correlation.)Create a correlation table for the variables in our data set. (Use analysis ToolPak or StatPlus:mac LE function Correlation.)Create a correlation table for the variables in our data set. (Use analysis ToolPak or StatPlus:mac LE function Correlation.)Create a correlation table for the variables in our data set. (Use analysis ToolPak or StatPlus:mac LE function Correlation.)
a. Reviewing the data levels from week 1, what variables can be used in a Pearson's Correlation table (which is what Excel produces)?Reviewing the data levels from week 1, what variables can be used in a Pearson's Correlation table (which is what Excel produces)?Reviewing the data levels from week 1, what variables can be used in a Pearson's Correlation table (which is what Excel produces)?Reviewing the data levels from week 1, what variables can be used in a Pearson's Correlation table (which is what Excel produces)?Reviewing the data levels from week 1, what variables can be used in a Pearson's Correlation table (which is what Excel produces)?Reviewing the data levels from week 1, what variables can be used in a Pearson's Correlation table (which is what Excel produces)?Reviewing the data levels from week 1, what variables can be used in a Pearson's Correlation table (which is what Excel produces)?Reviewing the data levels from week 1, what variables can be used in a Pearson's Correlation table (which is what Excel produces)?Reviewing the data levels from week 1, what variables can be used in a Pearson's Correlation table (which is what Excel produces)?
b. Place table here (C8):b. Place table here (C8):b. Place table here (C8):
c. Using r = approximately .28 as the signicant r value (at p = 0.05) for a correlation between 50 values, what variables areUsing r = approximately .28 as the signicant r value (at p = 0.05) for a correlation between 50 values, what variables areUsing r = approximately .28 as the signicant r value (at p = 0.05) for a correlation between 50 values, what variables areUsing r = approximately .28 as the signicant r value (at p = 0.05) for a correlation between 50 values, what variables areUsing r = approxi.
Computer Generated Items, Within-Template Variation, and the Impact on the Pa...Quinn Lathrop
Computer Generated Items, Within-Template Variation, and the Impact on the Parameters of Response Models.
Master's thesis talk related to Lathrop, Q.N., Cheng, Y. Item Cloning Variation and the Impact on the Parameters of Response Models. Psychometrika 82, 245–263 (2017). https://doi.org/10.1007/s11336-016-9513-1
GDC2019 - SEED - Towards Deep Generative Models in Game DevelopmentElectronic Arts / DICE
Deep learning is becoming ubiquitous in Machine Learning (ML) research, and it's also finding its place in industry-related applications. Specifically, deep generative models have proven incredibly useful at generating and remixing realistic content from scratch, making themselves a very appealing technology in the field of AI-enhanced content authoring. As part of this year's Machine Learning Tutorial at the Game Developers Conference 2019 (GDC), Jorge Del Val from SEED will cover in an accessible manner the fundamentals of deep generative modeling, including some common algorithms and architectures. He will also discuss applications to game development and explore some recent advances in the field.
The attendee will gain basic understanding of the fundamentals of generative models and how to implement them. Also, attendees will grasp potential applications in the field of game development to inspire their work and companies. This talk does not require a mathematical or machine learning background, although previous knowledge on either of those is beneficial.
Using Topological Data Analysis on your BigDataAnalyticsWeek
Synopsis:
Topological Data Analysis (TDA) is a framework for data analysis and machine learning and represents a breakthrough in how to effectively use geometric and topological information to solve 'Big Data' problems. TDA provides meaningful summaries (in a technical sense to be described) and insights into complex data problems. In this talk, Anthony will begin with an overview of TDA and describe the core algorithm that is utilized. This talk will include both the theory and real world problems that have been solved using TDA. After this talk, attendees will understand how the underlying TDA algorithm works and how it improves on existing “classical” data analysis techniques as well as how it provides a framework for many machine learning algorithms and tasks.
Speaker:
Anthony Bak, Senior Data Scientist, Ayasdi
Prior to coming to Ayasdi, Anthony was at Stanford University where he did a postdoc with Ayasdi co-founder Gunnar Carlsson, working on new methods and applications of Topological Data Analysis. He completed his Ph.D. work in algebraic geometry with applications to string theory at the University of Pennsylvania and ,along the way, he worked at the Max Planck Institute in Germany, Mount Holyoke College in Germany, and the American Institute of Mathematics in California.
Quantitative Data AnalysisReliability Analysis (Cronbach Alpha) Common Method...2023240532
Quantitative data Analysis
Overview
Reliability Analysis (Cronbach Alpha)
Common Method Bias (Harman Single Factor Test)
Frequency Analysis (Demographic)
Descriptive Analysis
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Subhajit Sahu
Abstract — Levelwise PageRank is an alternative method of PageRank computation which decomposes the input graph into a directed acyclic block-graph of strongly connected components, and processes them in topological order, one level at a time. This enables calculation for ranks in a distributed fashion without per-iteration communication, unlike the standard method where all vertices are processed in each iteration. It however comes with a precondition of the absence of dead ends in the input graph. Here, the native non-distributed performance of Levelwise PageRank was compared against Monolithic PageRank on a CPU as well as a GPU. To ensure a fair comparison, Monolithic PageRank was also performed on a graph where vertices were split by components. Results indicate that Levelwise PageRank is about as fast as Monolithic PageRank on the CPU, but quite a bit slower on the GPU. Slowdown on the GPU is likely caused by a large submission of small workloads, and expected to be non-issue when the computation is performed on massive graphs.
Adjusting primitives for graph : SHORT REPORT / NOTESSubhajit Sahu
Graph algorithms, like PageRank Compressed Sparse Row (CSR) is an adjacency-list based graph representation that is
Multiply with different modes (map)
1. Performance of sequential execution based vs OpenMP based vector multiply.
2. Comparing various launch configs for CUDA based vector multiply.
Sum with different storage types (reduce)
1. Performance of vector element sum using float vs bfloat16 as the storage type.
Sum with different modes (reduce)
1. Performance of sequential execution based vs OpenMP based vector element sum.
2. Performance of memcpy vs in-place based CUDA based vector element sum.
3. Comparing various launch configs for CUDA based vector element sum (memcpy).
4. Comparing various launch configs for CUDA based vector element sum (in-place).
Sum with in-place strategies of CUDA mode (reduce)
1. Comparing various launch configs for CUDA based vector element sum (in-place).
The Building Blocks of QuestDB, a Time Series Databasejavier ramirez
Talk Delivered at Valencia Codes Meetup 2024-06.
Traditionally, databases have treated timestamps just as another data type. However, when performing real-time analytics, timestamps should be first class citizens and we need rich time semantics to get the most out of our data. We also need to deal with ever growing datasets while keeping performant, which is as fun as it sounds.
It is no wonder time-series databases are now more popular than ever before. Join me in this session to learn about the internal architecture and building blocks of QuestDB, an open source time-series database designed for speed. We will also review a history of some of the changes we have gone over the past two years to deal with late and unordered data, non-blocking writes, read-replicas, or faster batch ingestion.
Data Centers - Striving Within A Narrow Range - Research Report - MCG - May 2...pchutichetpong
M Capital Group (“MCG”) expects to see demand and the changing evolution of supply, facilitated through institutional investment rotation out of offices and into work from home (“WFH”), while the ever-expanding need for data storage as global internet usage expands, with experts predicting 5.3 billion users by 2023. These market factors will be underpinned by technological changes, such as progressing cloud services and edge sites, allowing the industry to see strong expected annual growth of 13% over the next 4 years.
Whilst competitive headwinds remain, represented through the recent second bankruptcy filing of Sungard, which blames “COVID-19 and other macroeconomic trends including delayed customer spending decisions, insourcing and reductions in IT spending, energy inflation and reduction in demand for certain services”, the industry has seen key adjustments, where MCG believes that engineering cost management and technological innovation will be paramount to success.
MCG reports that the more favorable market conditions expected over the next few years, helped by the winding down of pandemic restrictions and a hybrid working environment will be driving market momentum forward. The continuous injection of capital by alternative investment firms, as well as the growing infrastructural investment from cloud service providers and social media companies, whose revenues are expected to grow over 3.6x larger by value in 2026, will likely help propel center provision and innovation. These factors paint a promising picture for the industry players that offset rising input costs and adapt to new technologies.
According to M Capital Group: “Specifically, the long-term cost-saving opportunities available from the rise of remote managing will likely aid value growth for the industry. Through margin optimization and further availability of capital for reinvestment, strong players will maintain their competitive foothold, while weaker players exit the market to balance supply and demand.”
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Data and AI
Round table discussion of vector databases, unstructured data, ai, big data, real-time, robots and Milvus.
A lively discussion with NJ Gen AI Meetup Lead, Prasad and Procure.FYI's Co-Found
4. Idea: Don’t explain the whole model,
just one prediction
Complex models are
inherently complex!
But a single prediction involves only a
small piece of that complexity.
Inputvalue
Outputvalue
4
5. Goal: Model agnostic interpretability
model prediction
magic explanation
What if we could view the model as a black box…
…and yet still be able to explain predictions?
data
Interpretable, accurate: choose two!
5 $
6. If only we had this magic box…
model prediction
magic explanation
data
Predictions from any complex model could be explained.
Prediction would be decoupled from explanation, reducing method lock-in.
Explanations from very different model types could be easily compared.
and $!
6
7. So let’s build it!
model prediction
data
7
magic explanation
8. How much money is someone likely to make?
model 31%
chance of making
> $50K annually
9. How much money is someone likely to make?
model 31%
chance of making
> $50K annually
Capital losses $0
Weekly hours 40
Occupation Protective-serv
Capital gains $0
Age 28
Marital status Married-civ-spouse
10. 10
chance of making > $50K annually
Base rate
26%
How did we get here?
15% 40%
Model prediction
31%
11. model 26%
chance of making
> 50K annually
Occupation Exec-managerial
Age 37
Relationship Wife
Years in school 14
Sex Female
Marital status Married-civ-spouse
No attributes are
given to the model
Base rate
12. model 25%
chance of making
> 50K annually
Capital losses $0
Weekly hours 40
Occupation Protective-serv
Capital losses $0
Age 28
Marital status Married-civ-spouse
13. 13
chance of making > $50K annually
Base rate
26%
15% 40%
No capital losses
Model prediction if we only know they had no capital losses
25%
14. 14
chance of making > $50K annually
Base rate
26%
15% 40%
Police/fire
Prediction if we know they had no capital losses and work in police/fire
24%
24. Large capital lossLarge capital gain
Young and single
Highly educated and married
Highly educated and single
Young and married
Divorced women
Married,typical education
Samplessorted by ESvalue similarity(B)
(A)
Bar width isequal to the
ESvalue for that input
Predictiedprobabilityofmaking>=50K
24
Samples clustered by explanation similarity
25. 25
chance of making > $50K annually
15% 40%
Explaining a single prediction from a model
with 500 decision trees
Unique optimal explanation under basic axioms from
cooperative game theory.
33. Car salesman example
33
Age
Weight
Is student
Imagine the explanation gx is a linear model of x’:
Age known to be 25
Weight known to be 150
Is student known to be 1
35. • Axiom 1 (Binarization)
• Axiom 2 (Linearity)
SHAP class of explanation methods
35
All methods that satisfy Axioms 1 and 2 are in the
Shapley Additive Explanation (SHAP) class.
Where 0 means “missing” and 1 means “observed”
An explanation is a linear model.
36. Given two natural axioms, there is only one
possible magic box in the SHAP class!
36
f f(x)
x
m gx
‘m’ is uniquely determined for all methods in the SHAP class under two axioms
38. Monotonicity axiom: If we make a new
model 𝑓′
𝑥 that is larger than 𝑓(𝑥)
whenever 𝑥𝑖
′
= 1 then 𝜙𝑖 𝑓′
, 𝑥 ≥ 𝜙𝑖 𝑓, 𝑥
38
f([0, 1, 1, 0, 0]) - f([0, 0, 1, 0, 0]) =
f([0, 1, 1, 1, 1]) - f([0, 0, 1, 1, 1]) =
f([0, 1, 0, 0, 0]) - f([0, 0, 0, 0, 0]) =
f([1, 1, 1, 0, 1]) - f([1, 0, 1, 0, 1]) =
f([1, 1, 1, 1, 1]) - f([1, 0, 1, 1, 1]) =
f([1, 1, 0, 0, 1]) - f([1, 0, 0, 0, 1]) =
𝜙𝑖 𝑓, 𝑥 =
Input feature i Input feature i
Output value difference
when adding 𝑥𝑖
′
i’th SHAP value for f
39. Monotonicity axiom: If we make a new
model 𝑓′
𝑥 that is larger than 𝑓(𝑥)
whenever 𝑥𝑖
′
= 1 then 𝜙𝑖 𝑓′
, 𝑥 ≥ 𝜙𝑖 𝑓, 𝑥
39
f’([0, 1, 1, 0, 0]) – f’([0, 0, 1, 0, 0]) =
f’([0, 1, 1, 1, 1]) – f’([0, 0, 1, 1, 1]) =
f’([0, 1, 0, 0, 0]) – f’([0, 0, 0, 0, 0]) =
f’([1, 1, 1, 0, 1]) – f’([1, 0, 1, 0, 1]) =
f’([1, 1, 1, 1, 1]) – f’([1, 0, 1, 1, 1]) =
f’([1, 1, 0, 0, 1]) – f’([1, 0, 0, 0, 1]) =
𝜙𝑖 𝑓′
, 𝑥 =
Input feature i Input feature i
Output value difference
when adding 𝑥𝑖
′
i’th SHAP value for f’
40. Proofs from coalitional game theory show there is only
one possible set of values 𝜙𝑖 that satisfy these axioms.
They are the Shapley values.
40
41. Modelagnostic
41
LIME
Shapley value sampling /
Quantitative Input Influence
Approximate the complex model near a given
prediction. - Ribeiro et al. 2016
Feature importance for a given prediction using
game theory. - Štrumbelj et al 2014, Datta et al. 2016
DeepLIFT
Difference from a reference explanations of
neural networks. – Shrikumar et al. 2016
Layer-wise relevance prop
Back propagates neural network explanations. -
Bach et al. 2015
Shapley regression values
Explain linear models in the presence of
collinearity. – Gromping et al. 2012
NeuralnetworksLinear
The SHAP class is large
42. Surprising unity!
Modelagnostic
42
LIME
Shapley regression values
NeuralnetworksLinear
The SHAP class has one
optimum, in the sense that it is
the only set of additive values
satisfying several desirable
properties.
DeepLIFT
Layer-wise relevance prop. SHAP
Shapley value sampling /
Quantitative Input Influence
class
43. Surprising unity!
Modelagnostic
43
LIME
Shapley regression values
NeuralnetworksLinear
The SHAP class has one
optimum, in the sense that it is
the only set of additive values
satisfying several desirable
properties.
DeepLIFT
Layer-wise relevance prop. SHAP
Shapley value sampling /
Quantitative Input Influence
class
44. SHAP class unifies in three ways:
44
Shapley/QIISHAP
1. Extends Shapley value sampling and Quantitative Input Influence.
2. Provides theoretically justified improvements and motivation for other methods.
3. Adapts other method’s to improve Shapley value estimation performance.
46. The LIME formalism of fitting a simple
interpretable model to a complex model locally
The loss function forcing g to well approximate f
A class of interpretable models
Kernel specifying what ‘local’ means
Optional regularization of g
But how do we pick 𝒢, L, 𝜴, and 𝝅 𝒙′?
46
SHAP
47. Surprise: If 𝒢 is linear models, and x’ is
binary then we are in the SHAP class!
This means the Shapley values are the only possible
solution satisfying efficiency and monotonicity.
47
Great! But what about the parameters L, 𝛺, and 𝜋 𝑥′?
48. We found a kernel and loss function that cause a local approximation
to reproduce the Shapley values.
The Shapley kernel
here, and let f x (S) = f (hx (1S )). If for all subsets S that do not contain i or j
f x (S [ { i} ) = f x (S [ { j } ) (4)
φi (f , x) = φj (f , x). This states that if two features contribute equally to the model
heir effects must bethe same.
tonicity. For any two models f and f 0
, if for all subsets S that do not contain i
f x (S [ { i} ) − f x (S) ≥ f 0
x (S [ { i} ) − f 0
x (S) (5)
φi (f , x) ≥ φi (f 0
, x). Thisstates that if observing afeature increases f morethan f 0
in
uations, then that feature’seffect should belarger for f than for f 0
.
of theseaxioms would lead to potentially confusing behavior. In 1985, Peyton Young
hat there is only one set of values that satisfies the aboveassumptions and they are
ues [7, 4]. ESvaluesareShapley values of expected valuefunctions, therefore they
ution to Equation 1 that conforms to Equation 2 and satisfies thethree axioms above.
of ESvaluesholdsover alargeclass of possible models, including theexamples used
aper that originally proposed this formalism [3].
pecific forms of x0
, L, and ⌦that lead to Shapley values asthesolution and they are:
⌦(g) = 0
⇡x 0(z0
) =
(M − 1)
(M choose |z0|)|z0|(M − |z0|)
X ⇥ ⇤
(6) 48
of theseaxioms would lead to potentially confusing behavior. In 1985, Peyton Young
hat there is only one set of values that satisfies the aboveassumptions and they are
ues [7, 4]. ESvaluesareShapley values of expected valuefunctions, therefore they
ution to Equation 1 that conforms to Equation 2 and satisfies thethree axioms above.
of ESvaluesholdsover alargeclass of possible models, including theexamples used
aper that originally proposed this formalism [3].
pecific forms of x0
, L, and ⌦that lead to Shapley values asthesolution and they are:
⌦(g) = 0
⇡x 0(z0
) =
(M − 1)
(M choose |z0|)|z0|(M − |z0|)
L(f , g, ⇡x0) =
X
z02 Z
⇥
f (h− 1
x (z0
)) − g(z0
)
⇤2
⇡x 0(z0
)
(6)
to note that ⇡x 0(z0
) = 1 when |z0
| 2 { 0, M } , which enforces φ0 = f x (; ) and
φi . In practicetheseinfiniteweightscan beavoided during optimization by analytically
o variables using these constraints. Figure 2A compares our Shapley kernel with
schosen heuristically. Theintuitiveconnection between linear regression and classical
estimates isthat classical Shapley value estimates arecomputed asthemean of many
s. Sincethemean isalso thebest least squares point estimate for aset of datapointsit
arch for aweighting kernel that causeslinear least squares regression to recapitulate
tonicity. For any two models f and f 0
, if for all subsets S that do not contain i
f x (S [ { i} ) − f x (S) ≥ f 0
x (S [ { i} ) − f 0
x (S) (5)
φi (f , x) ≥ φi (f 0
, x). Thisstates that if observing afeature increases f morethan f 0
in
uations, then that feature’seffect should belarger for f than for f 0
.
of theseaxioms would lead to potentially confusing behavior. In 1985, Peyton Young
hat there is only one set of values that satisfies the aboveassumptions and they are
ues [7, 4]. ESvaluesareShapley values of expected valuefunctions, therefore they
ution to Equation 1 that conforms to Equation 2 and satisfies thethree axioms above.
of ESvaluesholdsover alargeclass of possible models, including theexamples used
aper that originally proposed this formalism [3].
pecific forms of x0
, L, and ⌦that lead to Shapley values asthesolution and they are:
⌦(g) = 0
⇡x 0(z0
) =
(M − 1)
(M choose |z0|)|z0|(M − |z0|)
L(f , g, ⇡x0) =
X
z02 Z
⇥
f (h− 1
x (z0
)) − g(z0
)
⇤2
⇡x 0(z0
)
(6)
to note that ⇡x 0(z0
) = 1 when |z0
| 2 { 0, M } , which enforces φ0 = f x (; ) and
φi . In practicetheseinfiniteweightscan beavoided during optimization by analytically
There is no other kernel that satisfies the axioms and produces a different result.