The presentation describes the AI bias with adversarial learning.
It includes the AI Fairness 360 open source by IBM.
I presented this paper in the natural language processing lab as an undergraduate research assistant.
(July 9th, 2019)
The fifth lecture from the Machine Learning course series of lectures. It covers short history, basic types and most important principles of neural networks. A link to my github (https://github.com/skyfallen/MachineLearningPracticals) with practicals that I have designed for this course in both R and Python. I can share keynote files, contact me via e-mail: dmytro.fishman@ut.ee.
He Said, She Said: Finding and Fixing Bias in NLP (Natural Language Processin...Patrick Van Renterghem
Yves Peirsman presents several instances where bias has posed a risk to the successful adoption of NLP systems, and discusses what techniques exist to discover these biases before the systems are put in production.
The fifth lecture from the Machine Learning course series of lectures. It covers short history, basic types and most important principles of neural networks. A link to my github (https://github.com/skyfallen/MachineLearningPracticals) with practicals that I have designed for this course in both R and Python. I can share keynote files, contact me via e-mail: dmytro.fishman@ut.ee.
He Said, She Said: Finding and Fixing Bias in NLP (Natural Language Processin...Patrick Van Renterghem
Yves Peirsman presents several instances where bias has posed a risk to the successful adoption of NLP systems, and discusses what techniques exist to discover these biases before the systems are put in production.
Liên hệ page để tải tài liệu
https://www.facebook.com/garmentspace
My Blog: http://congnghemayblog.blogspot.com/
http://congnghemay123.blogspot.com/
Từ khóa tìm kiếm tài liệu : Wash jeans garment washing and dyeing, tài liệu ngành may, purpose of washing, definition of garment washing, tài liệu cắt may, sơ mi nam nữ, thiết kế áo sơ mi nam, thiết kế quần âu, thiết kế veston nam nữ, thiết kế áo dài, chân váy đầm liền thân, zipper, dây kéo trong ngành may, tài liệu ngành may, khóa kéo răng cưa, triển khai sản xuất, jacket nam, phân loại khóa kéo, tin học ngành may, bài giảng Accumark, Gerber Accumarkt, cad/cam ngành may, tài liệu ngành may, bộ tài liệu kỹ thuật ngành may dạng đầy đủ, vật liệu may, tài liệu ngành may, tài liệu về sợi, nguyên liệu dệt, kiểu dệt vải dệt thoi, kiểu dệt vải dệt kim, chỉ may, vật liệu dựng, bộ tài liệu kỹ thuật ngành may dạng đầy đủ, tiêu chuẩn kỹ thuật áo sơ mi nam, tài liệu kỹ thuật ngành may, tài liệu ngành may, nguồn gốc vải denim, lịch sử ra đời và phát triển quần jean, Levi's, Jeans, Levi Straus, Jacob Davis và Levis Strauss, CHẤT LIỆU DENIM, cắt may quần tây nam, quy trình may áo sơ mi căn bản, quần nam không ply, thiết kế áo sơ mi nam, thiết kế áo sơ mi nam theo tài liệu kỹ thuật, tài liệu cắt may,lịch sử ra đời và phát triển quần jean, vải denim, Levis strauss cha đẻ của quần jeans. Jeans skinny, street style áo sơ mi nam, tính vải may áo quần, sơ mi nam nữ, cắt may căn bản, thiết kế quần áo, tài liệu ngành may,máy 2 kim, máy may công nghiệp, two needle sewing machine, tài liệu ngành may, thiết bị ngành may, máy móc ngành may,Tiếng anh ngành may, english for gamrment technology, anh văn chuyên ngành may, may mặc thời trang, english, picture, Nhận biết và phân biệt các loại vải, cotton, chiffon, silk, woolCÁCH MAY – QUY CÁCH LẮP RÁP – QUY CÁCH ĐÁNH SỐTÀI LIỆU KỸ THUẬT NGÀNH MAY –TIÊU CHUẨN KỸ THUẬT – QUY CÁCH ĐÁNH SỐ - QUY CÁCH LẮP RÁP – QUY CÁCH MAY – QUY TRÌNH MAY – GẤP XẾP ĐÓNG GÓI
Nhận viết luận văn Đại học , thạc sĩ - Zalo: 0917.193.864
Tham khảo bảng giá dịch vụ viết bài tại: vietbaocaothuctap.net
Download luận văn thạc sĩ ngành toán giải tích với đề tài: Nghiên cứu Về cực trị hàm lồi, cho các bạn làm luận văn tham khảo
Tutorial on Generalization in Neural Fields, CVPR 2022 Tutorial on Neural Fie...Vincent Sitzmann
Slides for the "generalization" session of our CVPR 2022 tutorial on Neural Fields in Computer Vision.
Neural Fields are an emerging technique to parameterize signals that live in spatial coordinates plus time. They parameterize a signal as a continuous function that maps a space-time coordinate to whatever is at that spacetime coordinate - for instance, the geometry of a 3D scene could be encoded in a function that maps a 3D coordinate to whether that coordinate is occupied or not. A neural field parameterizes that function as a neural network.
In this session, I gave a high-level overview over how we may use neural fields as the output of a variety of inference algorithms, for instance to reconstruct a complete 3D shape from partial observations in the form of a pointcloud, or to reconstruct a 3D scene from only a single image.
You are free to use the slides for any purpose, as long as you keep a note on the slides that acknowledges their source.
Neural Fields database: https://neuralfields.cs.brown.edu/
Tutorial website: https://neuralfields.cs.brown.edu/cvpr22
Download luận văn thạc sĩ ngành xác suất và thống kê toán với đề tài: Một số phương pháp xây dựng độ đo và tích phân, cho các bạn làm luận văn tham khảo
Crf based named entity recognition using a korean lexical semantic networkDanbi Cho
They extracted the features for the named entity recognition task.
They use the UWordMap to learn the characteristics of the korean words.
(28th May, 2021)
I summarized the GPT models in this slide and compared the GPT1, GPT2, and GPT3.
GPT means Generative Pre-Training of a language model and was implemented based on the decoder structure of the transformer model.
(24th May, 2021)
Liên hệ page để tải tài liệu
https://www.facebook.com/garmentspace
My Blog: http://congnghemayblog.blogspot.com/
http://congnghemay123.blogspot.com/
Từ khóa tìm kiếm tài liệu : Wash jeans garment washing and dyeing, tài liệu ngành may, purpose of washing, definition of garment washing, tài liệu cắt may, sơ mi nam nữ, thiết kế áo sơ mi nam, thiết kế quần âu, thiết kế veston nam nữ, thiết kế áo dài, chân váy đầm liền thân, zipper, dây kéo trong ngành may, tài liệu ngành may, khóa kéo răng cưa, triển khai sản xuất, jacket nam, phân loại khóa kéo, tin học ngành may, bài giảng Accumark, Gerber Accumarkt, cad/cam ngành may, tài liệu ngành may, bộ tài liệu kỹ thuật ngành may dạng đầy đủ, vật liệu may, tài liệu ngành may, tài liệu về sợi, nguyên liệu dệt, kiểu dệt vải dệt thoi, kiểu dệt vải dệt kim, chỉ may, vật liệu dựng, bộ tài liệu kỹ thuật ngành may dạng đầy đủ, tiêu chuẩn kỹ thuật áo sơ mi nam, tài liệu kỹ thuật ngành may, tài liệu ngành may, nguồn gốc vải denim, lịch sử ra đời và phát triển quần jean, Levi's, Jeans, Levi Straus, Jacob Davis và Levis Strauss, CHẤT LIỆU DENIM, cắt may quần tây nam, quy trình may áo sơ mi căn bản, quần nam không ply, thiết kế áo sơ mi nam, thiết kế áo sơ mi nam theo tài liệu kỹ thuật, tài liệu cắt may,lịch sử ra đời và phát triển quần jean, vải denim, Levis strauss cha đẻ của quần jeans. Jeans skinny, street style áo sơ mi nam, tính vải may áo quần, sơ mi nam nữ, cắt may căn bản, thiết kế quần áo, tài liệu ngành may,máy 2 kim, máy may công nghiệp, two needle sewing machine, tài liệu ngành may, thiết bị ngành may, máy móc ngành may,Tiếng anh ngành may, english for gamrment technology, anh văn chuyên ngành may, may mặc thời trang, english, picture, Nhận biết và phân biệt các loại vải, cotton, chiffon, silk, woolCÁCH MAY – QUY CÁCH LẮP RÁP – QUY CÁCH ĐÁNH SỐTÀI LIỆU KỸ THUẬT NGÀNH MAY –TIÊU CHUẨN KỸ THUẬT – QUY CÁCH ĐÁNH SỐ - QUY CÁCH LẮP RÁP – QUY CÁCH MAY – QUY TRÌNH MAY – GẤP XẾP ĐÓNG GÓI
Nhận viết luận văn Đại học , thạc sĩ - Zalo: 0917.193.864
Tham khảo bảng giá dịch vụ viết bài tại: vietbaocaothuctap.net
Download luận văn thạc sĩ ngành toán giải tích với đề tài: Nghiên cứu Về cực trị hàm lồi, cho các bạn làm luận văn tham khảo
Tutorial on Generalization in Neural Fields, CVPR 2022 Tutorial on Neural Fie...Vincent Sitzmann
Slides for the "generalization" session of our CVPR 2022 tutorial on Neural Fields in Computer Vision.
Neural Fields are an emerging technique to parameterize signals that live in spatial coordinates plus time. They parameterize a signal as a continuous function that maps a space-time coordinate to whatever is at that spacetime coordinate - for instance, the geometry of a 3D scene could be encoded in a function that maps a 3D coordinate to whether that coordinate is occupied or not. A neural field parameterizes that function as a neural network.
In this session, I gave a high-level overview over how we may use neural fields as the output of a variety of inference algorithms, for instance to reconstruct a complete 3D shape from partial observations in the form of a pointcloud, or to reconstruct a 3D scene from only a single image.
You are free to use the slides for any purpose, as long as you keep a note on the slides that acknowledges their source.
Neural Fields database: https://neuralfields.cs.brown.edu/
Tutorial website: https://neuralfields.cs.brown.edu/cvpr22
Download luận văn thạc sĩ ngành xác suất và thống kê toán với đề tài: Một số phương pháp xây dựng độ đo và tích phân, cho các bạn làm luận văn tham khảo
Crf based named entity recognition using a korean lexical semantic networkDanbi Cho
They extracted the features for the named entity recognition task.
They use the UWordMap to learn the characteristics of the korean words.
(28th May, 2021)
I summarized the GPT models in this slide and compared the GPT1, GPT2, and GPT3.
GPT means Generative Pre-Training of a language model and was implemented based on the decoder structure of the transformer model.
(24th May, 2021)
Attention boosted deep networks for video classificationDanbi Cho
The presentation explains the integrating attention with CNN and LSTM.
This paper carried out the video classification task using the attention with CNNLSTM models.
(9th April 2021)
A survey on deep learning based approaches for action and gesture recognition...Danbi Cho
The presentation surveys the methodologies for action and gesture recognition tasks with deep learning models and feature engineering methods.
(6th April 2021)
ELECTRA_Pretraining Text Encoders as Discriminators rather than GeneratorsDanbi Cho
The presentation explains the ELECTRA model.
ELECTRA means 'Efficiently Learning an Encoder that Classifies Token Replacements Accurately'.
This paper proposes the replaced token detection and it is more compute-efficient than masked language models.
(11st March 2021)
A survey on automatic detection of hate speech in textDanbi Cho
The presentation survey on automatic detection of hate speech in the text.
It explains the motivation of the research, the definition of hate speech, and literature reviews.
(8th Febulary 2021)
Zero wall detecting zero-day web attacks through encoder-decoder recurrent ne...Danbi Cho
The presentation describes the zero-day detection using encoder-decoder recurrent neural networks while getting ideas from machine translation of natural language processing.
I presented this in a graduate class.
(Dec 2nd, 2020)
The presentation explains the decision tree and ensemble in machine learning.
I presented this at the Big data club for college students.
(Jan 31st, 2019)
The presentation explains the recurrent neural networks warp time.
It considers the invariance to time rescaling and invariance to time warpings with pure warpings and padding.
(Nov 18th, 2019)
Man is to computer programmer as woman is to homemaker debiasing word embeddingsDanbi Cho
This presentation describes the gender bias explaining the debiasing algorithms.
This paper uses the embedding method for debiasing.
I presented this paper in the natural language processing lab as an undergraduate research assistant.
(July 30th, 2019)
Situation recognition visual semantic role labeling for image understandingDanbi Cho
This presentation explains the situation recognition with visual semantic role labeling for image understanding.
I presented this paper in the natural language processing lab as an undergraduate research assistant.
(July 16th, 2019)
Gamify Your Mind; The Secret Sauce to Delivering Success, Continuously Improv...Shahin Sheidaei
Games are powerful teaching tools, fostering hands-on engagement and fun. But they require careful consideration to succeed. Join me to explore factors in running and selecting games, ensuring they serve as effective teaching tools. Learn to maintain focus on learning objectives while playing, and how to measure the ROI of gaming in education. Discover strategies for pitching gaming to leadership. This session offers insights, tips, and examples for coaches, team leads, and enterprise leaders seeking to teach from simple to complex concepts.
Providing Globus Services to Users of JASMIN for Environmental Data AnalysisGlobus
JASMIN is the UK’s high-performance data analysis platform for environmental science, operated by STFC on behalf of the UK Natural Environment Research Council (NERC). In addition to its role in hosting the CEDA Archive (NERC’s long-term repository for climate, atmospheric science & Earth observation data in the UK), JASMIN provides a collaborative platform to a community of around 2,000 scientists in the UK and beyond, providing nearly 400 environmental science projects with working space, compute resources and tools to facilitate their work. High-performance data transfer into and out of JASMIN has always been a key feature, with many scientists bringing model outputs from supercomputers elsewhere in the UK, to analyse against observational or other model data in the CEDA Archive. A growing number of JASMIN users are now realising the benefits of using the Globus service to provide reliable and efficient data movement and other tasks in this and other contexts. Further use cases involve long-distance (intercontinental) transfers to and from JASMIN, and collecting results from a mobile atmospheric radar system, pushing data to JASMIN via a lightweight Globus deployment. We provide details of how Globus fits into our current infrastructure, our experience of the recent migration to GCSv5.4, and of our interest in developing use of the wider ecosystem of Globus services for the benefit of our user community.
Why React Native as a Strategic Advantage for Startup Innovation.pdfayushiqss
Do you know that React Native is being increasingly adopted by startups as well as big companies in the mobile app development industry? Big names like Facebook, Instagram, and Pinterest have already integrated this robust open-source framework.
In fact, according to a report by Statista, the number of React Native developers has been steadily increasing over the years, reaching an estimated 1.9 million by the end of 2024. This means that the demand for this framework in the job market has been growing making it a valuable skill.
But what makes React Native so popular for mobile application development? It offers excellent cross-platform capabilities among other benefits. This way, with React Native, developers can write code once and run it on both iOS and Android devices thus saving time and resources leading to shorter development cycles hence faster time-to-market for your app.
Let’s take the example of a startup, which wanted to release their app on both iOS and Android at once. Through the use of React Native they managed to create an app and bring it into the market within a very short period. This helped them gain an advantage over their competitors because they had access to a large user base who were able to generate revenue quickly for them.
First Steps with Globus Compute Multi-User EndpointsGlobus
In this presentation we will share our experiences around getting started with the Globus Compute multi-user endpoint. Working with the Pharmacology group at the University of Auckland, we have previously written an application using Globus Compute that can offload computationally expensive steps in the researcher's workflows, which they wish to manage from their familiar Windows environments, onto the NeSI (New Zealand eScience Infrastructure) cluster. Some of the challenges we have encountered were that each researcher had to set up and manage their own single-user globus compute endpoint and that the workloads had varying resource requirements (CPUs, memory and wall time) between different runs. We hope that the multi-user endpoint will help to address these challenges and share an update on our progress here.
TROUBLESHOOTING 9 TYPES OF OUTOFMEMORYERRORTier1 app
Even though at surface level ‘java.lang.OutOfMemoryError’ appears as one single error; underlyingly there are 9 types of OutOfMemoryError. Each type of OutOfMemoryError has different causes, diagnosis approaches and solutions. This session equips you with the knowledge, tools, and techniques needed to troubleshoot and conquer OutOfMemoryError in all its forms, ensuring smoother, more efficient Java applications.
Modern design is crucial in today's digital environment, and this is especially true for SharePoint intranets. The design of these digital hubs is critical to user engagement and productivity enhancement. They are the cornerstone of internal collaboration and interaction within enterprises.
Multiple Your Crypto Portfolio with the Innovative Features of Advanced Crypt...Hivelance Technology
Cryptocurrency trading bots are computer programs designed to automate buying, selling, and managing cryptocurrency transactions. These bots utilize advanced algorithms and machine learning techniques to analyze market data, identify trading opportunities, and execute trades on behalf of their users. By automating the decision-making process, crypto trading bots can react to market changes faster than human traders
Hivelance, a leading provider of cryptocurrency trading bot development services, stands out as the premier choice for crypto traders and developers. Hivelance boasts a team of seasoned cryptocurrency experts and software engineers who deeply understand the crypto market and the latest trends in automated trading, Hivelance leverages the latest technologies and tools in the industry, including advanced AI and machine learning algorithms, to create highly efficient and adaptable crypto trading bots
Globus Connect Server Deep Dive - GlobusWorld 2024Globus
We explore the Globus Connect Server (GCS) architecture and experiment with advanced configuration options and use cases. This content is targeted at system administrators who are familiar with GCS and currently operate—or are planning to operate—broader deployments at their institution.
How Does XfilesPro Ensure Security While Sharing Documents in Salesforce?XfilesPro
Worried about document security while sharing them in Salesforce? Fret no more! Here are the top-notch security standards XfilesPro upholds to ensure strong security for your Salesforce documents while sharing with internal or external people.
To learn more, read the blog: https://www.xfilespro.com/how-does-xfilespro-make-document-sharing-secure-and-seamless-in-salesforce/
Accelerate Enterprise Software Engineering with PlatformlessWSO2
Key takeaways:
Challenges of building platforms and the benefits of platformless.
Key principles of platformless, including API-first, cloud-native middleware, platform engineering, and developer experience.
How Choreo enables the platformless experience.
How key concepts like application architecture, domain-driven design, zero trust, and cell-based architecture are inherently a part of Choreo.
Demo of an end-to-end app built and deployed on Choreo.
Code reviews are vital for ensuring good code quality. They serve as one of our last lines of defense against bugs and subpar code reaching production.
Yet, they often turn into annoying tasks riddled with frustration, hostility, unclear feedback and lack of standards. How can we improve this crucial process?
In this session we will cover:
- The Art of Effective Code Reviews
- Streamlining the Review Process
- Elevating Reviews with Automated Tools
By the end of this presentation, you'll have the knowledge on how to organize and improve your code review proces
Cyaniclab : Software Development Agency Portfolio.pdfCyanic lab
CyanicLab, an offshore custom software development company based in Sweden,India, Finland, is your go-to partner for startup development and innovative web design solutions. Our expert team specializes in crafting cutting-edge software tailored to meet the unique needs of startups and established enterprises alike. From conceptualization to execution, we offer comprehensive services including web and mobile app development, UI/UX design, and ongoing software maintenance. Ready to elevate your business? Contact CyanicLab today and let us propel your vision to success with our top-notch IT solutions.
SOCRadar Research Team: Latest Activities of IntelBrokerSOCRadar
The European Union Agency for Law Enforcement Cooperation (Europol) has suffered an alleged data breach after a notorious threat actor claimed to have exfiltrated data from its systems. Infamous data leaker IntelBroker posted on the even more infamous BreachForums hacking forum, saying that Europol suffered a data breach this month.
The alleged breach affected Europol agencies CCSE, EC3, Europol Platform for Experts, Law Enforcement Forum, and SIRIUS. Infiltration of these entities can disrupt ongoing investigations and compromise sensitive intelligence shared among international law enforcement agencies.
However, this is neither the first nor the last activity of IntekBroker. We have compiled for you what happened in the last few days. To track such hacker activities on dark web sources like hacker forums, private Telegram channels, and other hidden platforms where cyber threats often originate, you can check SOCRadar’s Dark Web News.
Stay Informed on Threat Actors’ Activity on the Dark Web with SOCRadar!
Enhancing Research Orchestration Capabilities at ORNL.pdfGlobus
Cross-facility research orchestration comes with ever-changing constraints regarding the availability and suitability of various compute and data resources. In short, a flexible data and processing fabric is needed to enable the dynamic redirection of data and compute tasks throughout the lifecycle of an experiment. In this talk, we illustrate how we easily leveraged Globus services to instrument the ACE research testbed at the Oak Ridge Leadership Computing Facility with flexible data and task orchestration capabilities.
Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...informapgpstrackings
Keep tabs on your field staff effortlessly with Informap Technology Centre LLC. Real-time tracking, task assignment, and smart features for efficient management. Request a live demo today!
For more details, visit us : https://informapuae.com/field-staff-tracking/
Into the Box Keynote Day 2: Unveiling amazing updates and announcements for modern CFML developers! Get ready for exciting releases and updates on Ortus tools and products. Stay tuned for cutting-edge innovations designed to boost your productivity.
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...Anthony Dahanne
Les Buildpacks existent depuis plus de 10 ans ! D’abord, ils étaient utilisés pour détecter et construire une application avant de la déployer sur certains PaaS. Ensuite, nous avons pu créer des images Docker (OCI) avec leur dernière génération, les Cloud Native Buildpacks (CNCF en incubation). Sont-ils une bonne alternative au Dockerfile ? Que sont les buildpacks Paketo ? Quelles communautés les soutiennent et comment ?
Venez le découvrir lors de cette session ignite
2. - 인구통계학적 집단에 대한 편견이 훈련 데이터에 존재할 때, 이에 따라 훈련된 모델 또한 편견이 포함된다.
- Protected group를 modeling하려는 adversary와 model을 예측하려는 predictor를 동시에 학습시켜,
편견을 완화시키고자 한다.
- Measurements for Fairness:
> Demographic Parity
> Equality of Odds
> Equality of Opportunity
X
data
Y
predict
Z
Protected
attribute
predictor
Adversary
Adversarial Debiasing
6. AI Fairness 360 (AIF360)
AI Fairness 360 (AIF 360)
> 인공지능 기술의 활용 과정에서 등장할 수 있는 편향성을 시정하기 위해 IBM에서 이를 open source 형태로 발표.
https://github.com/IBM/AIF360
- Dataset과 model에서의 “편향성(bias)”을 완화하기 위한 알고리즘과 평가지표에 대한 설명
- Tutorial과 demo notebook 공개
7. AI Fairness 360 (AIF360)
https://arxiv.org/pdf/1810.01943.pdf
8. AI Fairness 360 (AIF360)
Algorithm Method
pre-processing
:데이터 자체의 편향성 문제
Re-weighing
(Kamiran&Calders, 2012)
Optimized pre-processing
(Calmon et al.,2017)
Learning fair
representation(LFR)
(Zemel et al.,2013)
Disparate import remover
(Feldman et al.,2015)
In-processing
: 특정 feature의 가중치로 인해
생성된 모델의 편향성 문제
Adversarial Debiasing
(Zhang et al.,2018)
Prejudice remover
(Kamishima et al.,2012)
Post-processing
: Test dataset자체의 편향성 문제
Equalized odds post-
processing (Hardt et al.,2016)
Calibrated eq. odds
postprocessing (Pleiss et al.,2017)
Reject Option classification
(Kamiran et al.,2012)
pre-processing
In-processing
Post-processing
9. Adversarial Debiasing (in-processing)
: 예측 정확도를 최대화하고 동시에 예측으로부터 protected attribute를 결정할 수 있는 Adversary’s ability를 감소시키는 classifier를 학습한다.
즉, adversary가 이용할 수 있는 집단 간 차별 정보(privileged group & unprivileged group)를 예측에 전달할 수 없기 때문에 공정한 classifier가 된다.
Adult / Census Income Dataset
In-processing _ Adversarial Debiasing
10. - Income이 >$50K인지를 예측하는 데이터셋
- 해당 모델에 대해 “Equality of Odds”를 강화하고자 한다.
- Protected Attribute: Sex
- Privileged Group: Male / Unprivileged Group: Female
In-processing _ Adversarial Debiasing
11. - Epoch: 50
- Batch_size: 128
- Plain model: without debias / model: with debias
In-processing _ Adversarial Debiasing
12. Statistical Parity Difference
= Pr(Unprivileged group) – Pr(privileged group)
Fairness는 -0.1~0.1의 값으로 평가된다.
Equal Opportunity Difference
= true positive rate
value < 0 , privileged group의 이익 / value > 0, unprivileged group의 이익
Fairness는 -0.1~0.1의 값으로 평가된다.
Average Odds Difference
= (false positive rate + true positive rate) / 2
value < 0, privileged group의 이익 / value > 0, unprivileged group의 이익
Fairness는 -0.1~0.1의 값으로 평가된다.
Disparate Impact
= Pr(Unprivileged group) / Pr(privileged group)
value < 1 , privileged group의 이익 / value > 1, unprivileged group의 이익
Fairness는 0.8~1.2의 값으로 평가된다.
Theil Index
= generalized entrop
각각의 data에 대한 inequality을 의미한다.
Perfect fairness = 0 (value 값이 낮을수록 fairness / 높을수록 problematic)
In-processing _ Adversarial Debiasing
14. Pre-processing _ Reweighing
The German credit dataset
> Protected attribute: AGE
> algorithm: Reweighing (pre-processing)
(protected attribute에 따라 편향성을 줄이도록 데이터셋을 변형시킨다.)
Privileged group이 training dataset에서 17%의 positive한 결과를 갖는다.
즉, 이러한 bias한 결과를 완화해야한다.
15. The German credit dataset
> Protected attribute: AGE
> algorithm: Reweighing (pre-processing)
(protected attribute에 따라 편향성을 줄이도록 데이터셋을 변형시킨다.)
Re-weighing model (pre-processing) 모델을 학습한 결과,
이전의 편향성이 0으로 줄어든 것을 확인할 수 있다.
Re-weighing model: classification이전에 fairness를 확인하기 위해 feature들의 조합(group, label)에 가중치를 부여한다.
Pre-processing _ Reweighing
16. Post-processing _ calibrate eq odds postprocessing
The Adult / Census Income dataset
> Protected attribute: Sex
> algorithm: Calibrated_eq_odds postprocessing (post-processing)
Logistic
regression
17. The Adult / Census Income dataset
> Protected attribute: Sex
> algorithm: Calibrated_eq_odds postprocessing (post-processing)
Post-processing
Post-processing _ calibrate eq odds postprocessing
18. The Adult / Census Income dataset
> Protected attribute: Sex
> algorithm: Calibrated_eq_odds postprocessing (post-processing)
Post-processing _ calibrate eq odds postprocessing