SlideShare a Scribd company logo
1 of 43
Vertical
Federated Learning
- Presented by Afsana Khan
Federated Learning
“Federated learning is a machine learning setting where multiple entities (clients) collaborate in solving a
machine learning problem, under the coordination of a central server or service provider. Each client’s
raw data is stored locally and not exchanged or transferred; instead focused updates intended for
immediate aggregation are used to achieve the learning objective.”
Kairouz et al., Advances and open problems in federated learning, 2019
Taxonomy of Federated Learning
Data Partitioning
Use Case for Vertical Federated Learning
Steps in VFL
● Secure Data Alignment
● Secure Model Training
● Secure Evaluation
Step 1 - Secure Data Alignment
Step 1 - Secure Data Alignment
Monica Scannapieco, et al., 2007. Privacy Preserving Schema and Data Matching. https://doi.org/10.1145/1247480.1247553
Secure Model Training in VFL
Yang, et al., Federated Machine Learning: Concept and Applications
•Step 1: collaborator C creates encryption pairs,
send public key to A and B;
•Step 2: A and B encrypt and exchange the
intermediate results for gradient and loss
calculations;
•Step 3: A and B computes encrypted gradients
and adds additional mask, respectively, and B
also computes encrypted loss; A and B send
encrypted values to C;
•Step 4: C decrypts and send the decrypted
gradients and loss back to A and B; A and B
unmask the gradients, update the model
parameters accordingly.
Vertical Federated Linear Regression
Yang, et al., Federated Machine Learning: Concept and Applications
Vertical Federated Linear Regression
Yang, et al., Federated Machine Learning: Concept and Applications
Secure Evaluation in VFL
Yang, et al., Federated Machine Learning: Concept and Applications
Is the evaluation secure enough? Can C infer raw
data of A and B?
Possible Solution!!!
Secure Multiparty Computation (SMC)
Do we really need a coordinator?
(Yang et al., Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinator,
Existing Vertically Federated Learning Algorithms
•Linear regression
(Gascon, et al., Privacy-preserving distributed linear regression on high-dimensional data. Proceedings on Privacy Enhancing
Technologies, 2017(4):345-364,2017)
•Association rule-mining
(Vaidya, Clifton, Privacy preserving association rule mining in vertically partitioned data. In Proceedings of the eighth ACM
SIGKDD international conference on Knowledge discovery and data mining, pages 639-644. ACM, 2002.)
•K-means clustering
(Vaidya, Clifton. Privacy-preserving k-means clustering over vertically partitioned data. In Proceedings of the ninth ACM SIGKDD
international conference on Knowledge discovery and data mining, pages 206-215, 2003.)
•Logistic regression
(Hardy et al., Private federated learning on vertically partitioned data via entity resolution and additively homomorphic
encryption, arXiv:1711.10677, 2017.)
•Random forest
(Liu, et al., Federated forest. arXiv:1905.10053, 2019.)
•XGBoost
(Cheng, et al., Secureboost: A lossless federated learning framework. arXiv:1901.08755, 2019.)
Vertical Federated Algorithms
Vertical Federated Algorithms
(Liu, et al., A Communication-Efficient Collaborative Learning Framework for Distributed Features, arXiv:1912.11187)
Structured Literature Review on VFL
Structured Literature Review on VFL (Results)
A Khan, et al., Vertical Federated Learning: A Structured Literature Review
Categorization of Vertical Federated Learning Literature
A Khan, et al., Vertical Federated Learning: A Structured Literature Review
Improving Communication Overhead in VFL
A Khan, et al., Vertical Federated Learning: A Structured Literature Review
Improving Communication Overhead in VFL
A Khan, et al., Communication-Efficient Vertical Federated Learning
Improving Communication Overhead in VFL
A Khan, et al., Communication-Efficient Vertical Federated Learning
Improving Communication Overhead in VFL
A Khan, et al., Communication-Efficient Vertical Federated Learning
Feature Extraction Methods Datasets
● Principal Component Analysis
● Undercomplete Autoencoder
Evaluation Metrics
● Accuracy
● F1-Score
Improving Communication Overhead in VFL
A Khan, et al., Communication-Efficient Vertical Federated Learning
Feature Extraction Methods Datasets
● Principal Component Analysis
● Undercomplete Autoencoder
Evaluation Metrics
● Accuracy
● F1-Score
Improving Communication Overhead in VFL
A Khan, et al., Communication-Efficient Vertical Federated Learning
Undercomplete Autoencoder
Improving Communication Overhead in VFL
A Khan, et al., Communication-Efficient Vertical Federated Learning
Improving Communication Overhead in VFL
A Khan, et al., Communication-Efficient Vertical Federated Learning
Improving Communication Overhead in VFL
A Khan, et al., Communication-Efficient Vertical Federated Learning
Business Aspect of VFL
Motivation??
Incentive/Reward Allocation to Parties in VFL
● What is the contribution of the parties?
● What do they bring to the table?
● How to reward parties with incentive fairly?
● How to explain the allocated incentives to the parties?
Existing Approaches in FL for Incentive Allocation
Game Theory Auction Theory Contract Theory
Incentive Allocation in FL
Shapley Value
Stackelberg
Game
Only Shapley values have been explored so far for VFL settings!!
Designing Pipeline for Fair Incentive Allocation in VFL
Client Selection
Contribution
Measurement
Incentive Allocation Explanation
Open Challenges in VFL
● Communication Overhead
● Asynchronism
● Data Scarcity
● Data Redundancy
● Defense Mechanisms for Backdoor Attacks
● High Dimensions
● Fairness: Model Fairness, Collaborative Fairness
● Explainability
DEMO
Vanila VFL
EXPERIMENT WITH SYNTHETIC DATASET
Y = 2.0*x1 + 5*x2 + 3.0*x3 + 4.0*x4 + 1.0*x5 + 6.0*x6
Independent Variables (Features) : x1, x2, x3, x4, x5, x6
Dependent Variable (Target): Y
Linear Regression Model
Features, X = {x1….x6}
Number of training Samples = 7000
Number of testing samples: 3000
Learning Rate : 0.01
Epochs: 50
R2_Score: 0.99
Centralized Linear Regression
Target: Y
Number of training samples: 7000
Number of features: 2
X = (x1,x2)
Number of training samples: 7000
Number of features: 2
X = (x3,x4)
Number of training samples: 7000
Number of features: 2
X = (x5,x6)
Client1 Client2 Client3
Features, X = {x1….x6}
Number of training Samples = 7000
Number of testing samples: 3000
Vertical Partitioning of the Dataset
R2_Score: 0.3054
Linear Regression Model Linear Regression Model Linear Regression Model
Conventional Machine Learning
Target: Y
Number of training samples: 7000
Number of testing samples: 3000
Number of features: 2
X = (x1,x2)
Number of training samples: 7000
Number of testing samples: 3000
Number of features: 2
X = (x3,x4)
Number of training samples: 7000
Number of testing samples: 3000
Number of features: 2
X = (x5,x6)
Client1 Client2 Client3
Vertical Federated Linear Regression
Guest Party
(Client with Labels)
Host Party
Complete a forward propagation using
local data
Receive forward output or intermediate
results from Host Party
Calculate loss from loss function
Send loss to the host party
Compute gradients
Update local model
Complete a forward propagation using
local data
Send intermediate results to Guest Party
Receive loss computed from Guest Party
Compute gradients
Update local model
Comparison of Weights After Convergence
w1 w2 w3 w4 w5 w6
Actual
Weights
2.0 5.0 3.0 4.0 1.0 6.0
Weights after
convergence
(Centralized
Learning)
2.01 4.91 3.006 3.996 1.03 5.897
Weights after
convergence
(Vertical
Federated
Learning)
1.95 4.87 2.90 3.88 1.06 5.91
Logistic Regression Model
Contains Labels: Y
Number of training samples: 7000
Number of testing samples: 3000
Number of features: 2
X = (x1,x2)
Logistic Regression Model
Does not contain Labels
Number of training samples: 7000
Number of testing samples: 3000
Number of features: 2
X = (x3…x5)
Logistic Regression Model
Does not contain Labels
Number of training samples: 7000
Number of testing samples: 3000
Number of features: 2
X = (x6)
Client1: Guest Client2: Host Client3: Host
R2_SCORE: 0.99
Evaluation of model in VFL
Client1 Output Client2 Output Client3 Output
+ +
Frameworks
Thank You!!

More Related Content

What's hot

Compositional AI: Fusion of AI/ML Services
Compositional AI: Fusion of AI/ML ServicesCompositional AI: Fusion of AI/ML Services
Compositional AI: Fusion of AI/ML ServicesDebmalya Biswas
 
Machine Learning Project Lifecycle
Machine Learning Project LifecycleMachine Learning Project Lifecycle
Machine Learning Project LifecycleAbdelhak MAHMOUDI
 
Monetizing Big Data at Telecom Service Providers
Monetizing Big Data at Telecom Service ProvidersMonetizing Big Data at Telecom Service Providers
Monetizing Big Data at Telecom Service ProvidersDataWorks Summit
 
Suresh Poopandi_Generative AI On AWS-MidWestCommunityDay-Final.pdf
Suresh Poopandi_Generative AI On AWS-MidWestCommunityDay-Final.pdfSuresh Poopandi_Generative AI On AWS-MidWestCommunityDay-Final.pdf
Suresh Poopandi_Generative AI On AWS-MidWestCommunityDay-Final.pdfAWS Chicago
 
Latent dirichletallocation presentation
Latent dirichletallocation presentationLatent dirichletallocation presentation
Latent dirichletallocation presentationSoojung Hong
 
The emerging role of Generative AI in Healthcare..pdf
The emerging role of Generative AI in Healthcare..pdfThe emerging role of Generative AI in Healthcare..pdf
The emerging role of Generative AI in Healthcare..pdfBluebash LLC
 
Enabling Edge Processing & Surgical Suite Integration with AWS Snowball Edge ...
Enabling Edge Processing & Surgical Suite Integration with AWS Snowball Edge ...Enabling Edge Processing & Surgical Suite Integration with AWS Snowball Edge ...
Enabling Edge Processing & Surgical Suite Integration with AWS Snowball Edge ...Amazon Web Services
 
Chat GPT TEL Community of Practice
Chat GPT TEL Community of PracticeChat GPT TEL Community of Practice
Chat GPT TEL Community of PracticePeter Windle
 
Honeybadger of BFT Protocols
Honeybadger of BFT ProtocolsHoneybadger of BFT Protocols
Honeybadger of BFT ProtocolsYongraeJo
 
Active Retrieval Augmented Generation.pdf
Active Retrieval Augmented Generation.pdfActive Retrieval Augmented Generation.pdf
Active Retrieval Augmented Generation.pdfPo-Chuan Chen
 
GenAI in Research with Responsible AI
GenAI in Researchwith Responsible AIGenAI in Researchwith Responsible AI
GenAI in Research with Responsible AILiming Zhu
 
Multisensor Data Fusion : Techno Briefing
Multisensor Data Fusion : Techno BriefingMultisensor Data Fusion : Techno Briefing
Multisensor Data Fusion : Techno BriefingPaveen Juntama
 
Blockchain Applications in Healthcare
Blockchain Applications in HealthcareBlockchain Applications in Healthcare
Blockchain Applications in HealthcareCitiusTech
 
Uncover the mysteries of infrastructure as code (iac)!
Uncover the mysteries of infrastructure as code (iac)!Uncover the mysteries of infrastructure as code (iac)!
Uncover the mysteries of infrastructure as code (iac)!Prashant Kalkar
 
AI in Telecom: How artificial intelligence is reshaping the vision of telco i...
AI in Telecom: How artificial intelligence is reshaping the vision of telco i...AI in Telecom: How artificial intelligence is reshaping the vision of telco i...
AI in Telecom: How artificial intelligence is reshaping the vision of telco i...Data Driven Innovation
 
Ph.D. Qualifying Exam Presentation (McGill University, Department of Biology))
Ph.D. Qualifying Exam Presentation (McGill University, Department of Biology))Ph.D. Qualifying Exam Presentation (McGill University, Department of Biology))
Ph.D. Qualifying Exam Presentation (McGill University, Department of Biology))nouji87
 
AI and the Future of Healthcare, Siemens Healthineers
AI and the Future of Healthcare, Siemens HealthineersAI and the Future of Healthcare, Siemens Healthineers
AI and the Future of Healthcare, Siemens HealthineersLevi Shapiro
 
Application of Machine Learning in Cyber Security
Application of Machine Learning in Cyber SecurityApplication of Machine Learning in Cyber Security
Application of Machine Learning in Cyber SecurityDr. Umesh Rao.Hodeghatta
 

What's hot (20)

Federated Learning
Federated LearningFederated Learning
Federated Learning
 
Compositional AI: Fusion of AI/ML Services
Compositional AI: Fusion of AI/ML ServicesCompositional AI: Fusion of AI/ML Services
Compositional AI: Fusion of AI/ML Services
 
Machine Learning Project Lifecycle
Machine Learning Project LifecycleMachine Learning Project Lifecycle
Machine Learning Project Lifecycle
 
Monetizing Big Data at Telecom Service Providers
Monetizing Big Data at Telecom Service ProvidersMonetizing Big Data at Telecom Service Providers
Monetizing Big Data at Telecom Service Providers
 
Suresh Poopandi_Generative AI On AWS-MidWestCommunityDay-Final.pdf
Suresh Poopandi_Generative AI On AWS-MidWestCommunityDay-Final.pdfSuresh Poopandi_Generative AI On AWS-MidWestCommunityDay-Final.pdf
Suresh Poopandi_Generative AI On AWS-MidWestCommunityDay-Final.pdf
 
Latent dirichletallocation presentation
Latent dirichletallocation presentationLatent dirichletallocation presentation
Latent dirichletallocation presentation
 
A petri-net
A petri-netA petri-net
A petri-net
 
The emerging role of Generative AI in Healthcare..pdf
The emerging role of Generative AI in Healthcare..pdfThe emerging role of Generative AI in Healthcare..pdf
The emerging role of Generative AI in Healthcare..pdf
 
Enabling Edge Processing & Surgical Suite Integration with AWS Snowball Edge ...
Enabling Edge Processing & Surgical Suite Integration with AWS Snowball Edge ...Enabling Edge Processing & Surgical Suite Integration with AWS Snowball Edge ...
Enabling Edge Processing & Surgical Suite Integration with AWS Snowball Edge ...
 
Chat GPT TEL Community of Practice
Chat GPT TEL Community of PracticeChat GPT TEL Community of Practice
Chat GPT TEL Community of Practice
 
Honeybadger of BFT Protocols
Honeybadger of BFT ProtocolsHoneybadger of BFT Protocols
Honeybadger of BFT Protocols
 
Active Retrieval Augmented Generation.pdf
Active Retrieval Augmented Generation.pdfActive Retrieval Augmented Generation.pdf
Active Retrieval Augmented Generation.pdf
 
GenAI in Research with Responsible AI
GenAI in Researchwith Responsible AIGenAI in Researchwith Responsible AI
GenAI in Research with Responsible AI
 
Multisensor Data Fusion : Techno Briefing
Multisensor Data Fusion : Techno BriefingMultisensor Data Fusion : Techno Briefing
Multisensor Data Fusion : Techno Briefing
 
Blockchain Applications in Healthcare
Blockchain Applications in HealthcareBlockchain Applications in Healthcare
Blockchain Applications in Healthcare
 
Uncover the mysteries of infrastructure as code (iac)!
Uncover the mysteries of infrastructure as code (iac)!Uncover the mysteries of infrastructure as code (iac)!
Uncover the mysteries of infrastructure as code (iac)!
 
AI in Telecom: How artificial intelligence is reshaping the vision of telco i...
AI in Telecom: How artificial intelligence is reshaping the vision of telco i...AI in Telecom: How artificial intelligence is reshaping the vision of telco i...
AI in Telecom: How artificial intelligence is reshaping the vision of telco i...
 
Ph.D. Qualifying Exam Presentation (McGill University, Department of Biology))
Ph.D. Qualifying Exam Presentation (McGill University, Department of Biology))Ph.D. Qualifying Exam Presentation (McGill University, Department of Biology))
Ph.D. Qualifying Exam Presentation (McGill University, Department of Biology))
 
AI and the Future of Healthcare, Siemens Healthineers
AI and the Future of Healthcare, Siemens HealthineersAI and the Future of Healthcare, Siemens Healthineers
AI and the Future of Healthcare, Siemens Healthineers
 
Application of Machine Learning in Cyber Security
Application of Machine Learning in Cyber SecurityApplication of Machine Learning in Cyber Security
Application of Machine Learning in Cyber Security
 

Similar to Vertical Federated Learning.pptx

Adversarial and reinforcement learning-based approaches to information retrieval
Adversarial and reinforcement learning-based approaches to information retrievalAdversarial and reinforcement learning-based approaches to information retrieval
Adversarial and reinforcement learning-based approaches to information retrievalBhaskar Mitra
 
Serving Information Needs of Knowledge Workers
Serving Information Needs of Knowledge WorkersServing Information Needs of Knowledge Workers
Serving Information Needs of Knowledge WorkersDebdoot Mukherjee
 
Advances in Exploratory Data Analysis, Visualisation and Quality for Data Cen...
Advances in Exploratory Data Analysis, Visualisation and Quality for Data Cen...Advances in Exploratory Data Analysis, Visualisation and Quality for Data Cen...
Advances in Exploratory Data Analysis, Visualisation and Quality for Data Cen...Hima Patel
 
Data-centric AI and the convergence of data and model engineering: opportunit...
Data-centric AI and the convergence of data and model engineering:opportunit...Data-centric AI and the convergence of data and model engineering:opportunit...
Data-centric AI and the convergence of data and model engineering: opportunit...Paolo Missier
 
Incentive Compatible Privacy Preserving Data Analysis
Incentive Compatible Privacy Preserving Data AnalysisIncentive Compatible Privacy Preserving Data Analysis
Incentive Compatible Privacy Preserving Data Analysisrupasri mupparthi
 
IRJET- Online Course Recommendation System
IRJET- Online Course Recommendation SystemIRJET- Online Course Recommendation System
IRJET- Online Course Recommendation SystemIRJET Journal
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnBenjamin Bengfort
 
Artificial intelligence and IoT
Artificial intelligence and IoTArtificial intelligence and IoT
Artificial intelligence and IoTVeselin Pizurica
 
Water Quality Index Calculation of River Ganga using Decision Tree Algorithm
Water Quality Index Calculation of River Ganga using Decision Tree AlgorithmWater Quality Index Calculation of River Ganga using Decision Tree Algorithm
Water Quality Index Calculation of River Ganga using Decision Tree AlgorithmIRJET Journal
 
IRJET - House Price Predictor using ML through Artificial Neural Network
IRJET - House Price Predictor using ML through Artificial Neural NetworkIRJET - House Price Predictor using ML through Artificial Neural Network
IRJET - House Price Predictor using ML through Artificial Neural NetworkIRJET Journal
 
IRJET- Stabilization of Black Cotton Soil using Rice Husk Ash and Lime
IRJET- Stabilization of Black Cotton Soil using Rice Husk Ash and LimeIRJET- Stabilization of Black Cotton Soil using Rice Husk Ash and Lime
IRJET- Stabilization of Black Cotton Soil using Rice Husk Ash and LimeIRJET Journal
 
IRJET- Student Placement Prediction using Machine Learning
IRJET- Student Placement Prediction using Machine LearningIRJET- Student Placement Prediction using Machine Learning
IRJET- Student Placement Prediction using Machine LearningIRJET Journal
 
[RecSys 2014] Deviation-Based and Similarity-Based Contextual SLIM Recommenda...
[RecSys 2014] Deviation-Based and Similarity-Based Contextual SLIM Recommenda...[RecSys 2014] Deviation-Based and Similarity-Based Contextual SLIM Recommenda...
[RecSys 2014] Deviation-Based and Similarity-Based Contextual SLIM Recommenda...YONG ZHENG
 
Evaluate deep q learning for sequential targeted marketing with 10-fold cross...
Evaluate deep q learning for sequential targeted marketing with 10-fold cross...Evaluate deep q learning for sequential targeted marketing with 10-fold cross...
Evaluate deep q learning for sequential targeted marketing with 10-fold cross...Jian Wu
 
Knowledge Distillation for Federated Learning: a Practical Guide
Knowledge Distillation for Federated Learning: a Practical GuideKnowledge Distillation for Federated Learning: a Practical Guide
Knowledge Distillation for Federated Learning: a Practical GuideXiachongFeng
 
IRJET - Recommendations Engine with Multi-Objective Contextual Bandits (U...
IRJET -  	  Recommendations Engine with Multi-Objective Contextual Bandits (U...IRJET -  	  Recommendations Engine with Multi-Objective Contextual Bandits (U...
IRJET - Recommendations Engine with Multi-Objective Contextual Bandits (U...IRJET Journal
 
Data Mining and the Web_Past_Present and Future
Data Mining and the Web_Past_Present and FutureData Mining and the Web_Past_Present and Future
Data Mining and the Web_Past_Present and Futurefeiwin
 
Performance analysis of KNN & K-Means using internet advertisements data
Performance analysis of KNN & K-Means using internet advertisements dataPerformance analysis of KNN & K-Means using internet advertisements data
Performance analysis of KNN & K-Means using internet advertisements dataMuhammad GulRaj
 

Similar to Vertical Federated Learning.pptx (20)

Adversarial and reinforcement learning-based approaches to information retrieval
Adversarial and reinforcement learning-based approaches to information retrievalAdversarial and reinforcement learning-based approaches to information retrieval
Adversarial and reinforcement learning-based approaches to information retrieval
 
Serving Information Needs of Knowledge Workers
Serving Information Needs of Knowledge WorkersServing Information Needs of Knowledge Workers
Serving Information Needs of Knowledge Workers
 
AI and Deep Learning
AI and Deep Learning AI and Deep Learning
AI and Deep Learning
 
Advances in Exploratory Data Analysis, Visualisation and Quality for Data Cen...
Advances in Exploratory Data Analysis, Visualisation and Quality for Data Cen...Advances in Exploratory Data Analysis, Visualisation and Quality for Data Cen...
Advances in Exploratory Data Analysis, Visualisation and Quality for Data Cen...
 
Data-centric AI and the convergence of data and model engineering: opportunit...
Data-centric AI and the convergence of data and model engineering:opportunit...Data-centric AI and the convergence of data and model engineering:opportunit...
Data-centric AI and the convergence of data and model engineering: opportunit...
 
Incentive Compatible Privacy Preserving Data Analysis
Incentive Compatible Privacy Preserving Data AnalysisIncentive Compatible Privacy Preserving Data Analysis
Incentive Compatible Privacy Preserving Data Analysis
 
IRJET- Online Course Recommendation System
IRJET- Online Course Recommendation SystemIRJET- Online Course Recommendation System
IRJET- Online Course Recommendation System
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-Learn
 
Artificial intelligence and IoT
Artificial intelligence and IoTArtificial intelligence and IoT
Artificial intelligence and IoT
 
Water Quality Index Calculation of River Ganga using Decision Tree Algorithm
Water Quality Index Calculation of River Ganga using Decision Tree AlgorithmWater Quality Index Calculation of River Ganga using Decision Tree Algorithm
Water Quality Index Calculation of River Ganga using Decision Tree Algorithm
 
IRJET - House Price Predictor using ML through Artificial Neural Network
IRJET - House Price Predictor using ML through Artificial Neural NetworkIRJET - House Price Predictor using ML through Artificial Neural Network
IRJET - House Price Predictor using ML through Artificial Neural Network
 
IRJET- Stabilization of Black Cotton Soil using Rice Husk Ash and Lime
IRJET- Stabilization of Black Cotton Soil using Rice Husk Ash and LimeIRJET- Stabilization of Black Cotton Soil using Rice Husk Ash and Lime
IRJET- Stabilization of Black Cotton Soil using Rice Husk Ash and Lime
 
IRJET- Student Placement Prediction using Machine Learning
IRJET- Student Placement Prediction using Machine LearningIRJET- Student Placement Prediction using Machine Learning
IRJET- Student Placement Prediction using Machine Learning
 
ICMCSI 2023 PPT 1074.pptx
ICMCSI 2023 PPT 1074.pptxICMCSI 2023 PPT 1074.pptx
ICMCSI 2023 PPT 1074.pptx
 
[RecSys 2014] Deviation-Based and Similarity-Based Contextual SLIM Recommenda...
[RecSys 2014] Deviation-Based and Similarity-Based Contextual SLIM Recommenda...[RecSys 2014] Deviation-Based and Similarity-Based Contextual SLIM Recommenda...
[RecSys 2014] Deviation-Based and Similarity-Based Contextual SLIM Recommenda...
 
Evaluate deep q learning for sequential targeted marketing with 10-fold cross...
Evaluate deep q learning for sequential targeted marketing with 10-fold cross...Evaluate deep q learning for sequential targeted marketing with 10-fold cross...
Evaluate deep q learning for sequential targeted marketing with 10-fold cross...
 
Knowledge Distillation for Federated Learning: a Practical Guide
Knowledge Distillation for Federated Learning: a Practical GuideKnowledge Distillation for Federated Learning: a Practical Guide
Knowledge Distillation for Federated Learning: a Practical Guide
 
IRJET - Recommendations Engine with Multi-Objective Contextual Bandits (U...
IRJET -  	  Recommendations Engine with Multi-Objective Contextual Bandits (U...IRJET -  	  Recommendations Engine with Multi-Objective Contextual Bandits (U...
IRJET - Recommendations Engine with Multi-Objective Contextual Bandits (U...
 
Data Mining and the Web_Past_Present and Future
Data Mining and the Web_Past_Present and FutureData Mining and the Web_Past_Present and Future
Data Mining and the Web_Past_Present and Future
 
Performance analysis of KNN & K-Means using internet advertisements data
Performance analysis of KNN & K-Means using internet advertisements dataPerformance analysis of KNN & K-Means using internet advertisements data
Performance analysis of KNN & K-Means using internet advertisements data
 

Recently uploaded

Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Educationpboyjonauth
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformChameera Dedduwage
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdfSoniaTolstoy
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Celine George
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Sapana Sha
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...EduSkills OECD
 
Arihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdfArihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdfchloefrazer622
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104misteraugie
 
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdfssuser54595a
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingTechSoup
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)eniolaolutunde
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactPECB
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionSafetyChain Software
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityGeoBlogs
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...Marc Dusseiller Dusjagr
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxSayali Powar
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Krashi Coaching
 

Recently uploaded (20)

Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Education
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy Reform
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
 
Staff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSDStaff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSD
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
 
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdfTataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
Arihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdfArihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdf
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104
 
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory Inspection
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activity
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
 

Vertical Federated Learning.pptx

  • 2. Federated Learning “Federated learning is a machine learning setting where multiple entities (clients) collaborate in solving a machine learning problem, under the coordination of a central server or service provider. Each client’s raw data is stored locally and not exchanged or transferred; instead focused updates intended for immediate aggregation are used to achieve the learning objective.” Kairouz et al., Advances and open problems in federated learning, 2019
  • 5. Use Case for Vertical Federated Learning
  • 6. Steps in VFL ● Secure Data Alignment ● Secure Model Training ● Secure Evaluation
  • 7. Step 1 - Secure Data Alignment
  • 8. Step 1 - Secure Data Alignment Monica Scannapieco, et al., 2007. Privacy Preserving Schema and Data Matching. https://doi.org/10.1145/1247480.1247553
  • 9. Secure Model Training in VFL Yang, et al., Federated Machine Learning: Concept and Applications •Step 1: collaborator C creates encryption pairs, send public key to A and B; •Step 2: A and B encrypt and exchange the intermediate results for gradient and loss calculations; •Step 3: A and B computes encrypted gradients and adds additional mask, respectively, and B also computes encrypted loss; A and B send encrypted values to C; •Step 4: C decrypts and send the decrypted gradients and loss back to A and B; A and B unmask the gradients, update the model parameters accordingly.
  • 10. Vertical Federated Linear Regression Yang, et al., Federated Machine Learning: Concept and Applications
  • 11. Vertical Federated Linear Regression Yang, et al., Federated Machine Learning: Concept and Applications
  • 12. Secure Evaluation in VFL Yang, et al., Federated Machine Learning: Concept and Applications Is the evaluation secure enough? Can C infer raw data of A and B? Possible Solution!!! Secure Multiparty Computation (SMC)
  • 13. Do we really need a coordinator? (Yang et al., Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinator,
  • 14. Existing Vertically Federated Learning Algorithms •Linear regression (Gascon, et al., Privacy-preserving distributed linear regression on high-dimensional data. Proceedings on Privacy Enhancing Technologies, 2017(4):345-364,2017) •Association rule-mining (Vaidya, Clifton, Privacy preserving association rule mining in vertically partitioned data. In Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, pages 639-644. ACM, 2002.) •K-means clustering (Vaidya, Clifton. Privacy-preserving k-means clustering over vertically partitioned data. In Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, pages 206-215, 2003.) •Logistic regression (Hardy et al., Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption, arXiv:1711.10677, 2017.) •Random forest (Liu, et al., Federated forest. arXiv:1905.10053, 2019.) •XGBoost (Cheng, et al., Secureboost: A lossless federated learning framework. arXiv:1901.08755, 2019.)
  • 16. Vertical Federated Algorithms (Liu, et al., A Communication-Efficient Collaborative Learning Framework for Distributed Features, arXiv:1912.11187)
  • 18. Structured Literature Review on VFL (Results) A Khan, et al., Vertical Federated Learning: A Structured Literature Review
  • 19. Categorization of Vertical Federated Learning Literature A Khan, et al., Vertical Federated Learning: A Structured Literature Review
  • 20. Improving Communication Overhead in VFL A Khan, et al., Vertical Federated Learning: A Structured Literature Review
  • 21. Improving Communication Overhead in VFL A Khan, et al., Communication-Efficient Vertical Federated Learning
  • 22. Improving Communication Overhead in VFL A Khan, et al., Communication-Efficient Vertical Federated Learning
  • 23. Improving Communication Overhead in VFL A Khan, et al., Communication-Efficient Vertical Federated Learning Feature Extraction Methods Datasets ● Principal Component Analysis ● Undercomplete Autoencoder Evaluation Metrics ● Accuracy ● F1-Score
  • 24. Improving Communication Overhead in VFL A Khan, et al., Communication-Efficient Vertical Federated Learning Feature Extraction Methods Datasets ● Principal Component Analysis ● Undercomplete Autoencoder Evaluation Metrics ● Accuracy ● F1-Score
  • 25. Improving Communication Overhead in VFL A Khan, et al., Communication-Efficient Vertical Federated Learning Undercomplete Autoencoder
  • 26. Improving Communication Overhead in VFL A Khan, et al., Communication-Efficient Vertical Federated Learning
  • 27. Improving Communication Overhead in VFL A Khan, et al., Communication-Efficient Vertical Federated Learning
  • 28. Improving Communication Overhead in VFL A Khan, et al., Communication-Efficient Vertical Federated Learning
  • 29. Business Aspect of VFL Motivation??
  • 30. Incentive/Reward Allocation to Parties in VFL ● What is the contribution of the parties? ● What do they bring to the table? ● How to reward parties with incentive fairly? ● How to explain the allocated incentives to the parties?
  • 31. Existing Approaches in FL for Incentive Allocation Game Theory Auction Theory Contract Theory Incentive Allocation in FL Shapley Value Stackelberg Game Only Shapley values have been explored so far for VFL settings!!
  • 32. Designing Pipeline for Fair Incentive Allocation in VFL Client Selection Contribution Measurement Incentive Allocation Explanation
  • 33. Open Challenges in VFL ● Communication Overhead ● Asynchronism ● Data Scarcity ● Data Redundancy ● Defense Mechanisms for Backdoor Attacks ● High Dimensions ● Fairness: Model Fairness, Collaborative Fairness ● Explainability
  • 35. EXPERIMENT WITH SYNTHETIC DATASET Y = 2.0*x1 + 5*x2 + 3.0*x3 + 4.0*x4 + 1.0*x5 + 6.0*x6 Independent Variables (Features) : x1, x2, x3, x4, x5, x6 Dependent Variable (Target): Y
  • 36. Linear Regression Model Features, X = {x1….x6} Number of training Samples = 7000 Number of testing samples: 3000 Learning Rate : 0.01 Epochs: 50 R2_Score: 0.99 Centralized Linear Regression
  • 37. Target: Y Number of training samples: 7000 Number of features: 2 X = (x1,x2) Number of training samples: 7000 Number of features: 2 X = (x3,x4) Number of training samples: 7000 Number of features: 2 X = (x5,x6) Client1 Client2 Client3 Features, X = {x1….x6} Number of training Samples = 7000 Number of testing samples: 3000 Vertical Partitioning of the Dataset
  • 38. R2_Score: 0.3054 Linear Regression Model Linear Regression Model Linear Regression Model Conventional Machine Learning Target: Y Number of training samples: 7000 Number of testing samples: 3000 Number of features: 2 X = (x1,x2) Number of training samples: 7000 Number of testing samples: 3000 Number of features: 2 X = (x3,x4) Number of training samples: 7000 Number of testing samples: 3000 Number of features: 2 X = (x5,x6) Client1 Client2 Client3
  • 39. Vertical Federated Linear Regression Guest Party (Client with Labels) Host Party Complete a forward propagation using local data Receive forward output or intermediate results from Host Party Calculate loss from loss function Send loss to the host party Compute gradients Update local model Complete a forward propagation using local data Send intermediate results to Guest Party Receive loss computed from Guest Party Compute gradients Update local model
  • 40. Comparison of Weights After Convergence w1 w2 w3 w4 w5 w6 Actual Weights 2.0 5.0 3.0 4.0 1.0 6.0 Weights after convergence (Centralized Learning) 2.01 4.91 3.006 3.996 1.03 5.897 Weights after convergence (Vertical Federated Learning) 1.95 4.87 2.90 3.88 1.06 5.91
  • 41. Logistic Regression Model Contains Labels: Y Number of training samples: 7000 Number of testing samples: 3000 Number of features: 2 X = (x1,x2) Logistic Regression Model Does not contain Labels Number of training samples: 7000 Number of testing samples: 3000 Number of features: 2 X = (x3…x5) Logistic Regression Model Does not contain Labels Number of training samples: 7000 Number of testing samples: 3000 Number of features: 2 X = (x6) Client1: Guest Client2: Host Client3: Host R2_SCORE: 0.99 Evaluation of model in VFL Client1 Output Client2 Output Client3 Output + +