Fair Multi-party Machine Learning -- a Game Theoretic approach

2019-11-22 · Zhiliang Chen

High performance machine learning models have become highly dependent on the availability of large quantity and quality of training data. To achieve this, various central agencies such as the government have suggested for different data providers to pool their data together to learn a unified predictive model, which performs better. However, these providers are usually profit-driven and would only agree to participate inthe data sharing process if the process is deemed both profitable and fair for themselves. Due to the lack of existing literature, it is unclear whether a fair and stable outcome is possible in such data sharing processes. Hence, we wish to investigate the outcomes surrounding these scenarios and study if data providers would even agree to collaborate in the first place. Tapping on cooperative game concepts in Game Theory, we introduce the data sharing process between a group of agents as a new class of cooperative games with modified definition of stability and fairness. Using these new definitions, we then theoretically study the optimal and suboptimal outcomes of such data sharing processes and their sensitivity to perturbation.Through experiments, we present intuitive insights regarding theoretical results analysed in this paper and discuss various ways in which data can be valued reasonably.

📄 PDF Abstract BibTeX arXiv:1911.11555

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning Fairness

Fairness-Aware Performance Evaluation for Multi-Party Multi-Objective Optimization

2026-01-30 · Zifan Zhao, Peilan Xu, Wenjian Luo arxiv

In multiparty multiobjective optimization problems, solution sets are usually evaluated using classical performance metrics, aggregated across DMs. However, such mean-based evaluations may be unfair by favoring certain p…

Decision Making

Collaborative Machine Learning with Incentive-Aware Model Rewards

2020-10-24 · ICML 2020 1 · Rachael Hwee Ling Sim, Yehong Zhang, Mun Choon Chan, Bryan Kian Hsiang Low

Collaborative machine learning (ML) is an appealing paradigm to build high-quality ML models by training on the aggregated data from many parties. However, these parties are only willing to share their data when given en…

BIG-bench Machine Learning Fairness

Incentive Allocation in Vertical Federated Learning Based on Bankruptcy Problem

2023-07-07 · Afsana Khan, Marijn ten Thij, Frank Thuijsman, Anna Wilbik

Vertical federated learning (VFL) is a promising approach for collaboratively training machine learning models using private data partitioned vertically across different parties. Ideally in a VFL setting, the active part…

Fairness Federated Learning Privacy Preserving Vertical Federated Learning

A Game Theoretic Approach for Demand Response Allocation among Strategic Prosumers in Regulated Distribution Utilities

2021-10-04 · Sayyid Mohssen Sajjadi, Meng Wu

This paper studies an optimal allocation of demand response (DR) provisions among strategic photovoltaic (PV) prosumers, through third-party DR providers which operate within the territory of the regulated distribution u…

Fairness in Multi-Agent Sequential Decision-Making

2014-12-01 · NeurIPS 2014 12 · Chongjie Zhang, Julie A. Shah

We define a fairness solution criterion for multi-agent decision-making problems, where agents have local interests. This new criterion aims to maximize the worst performance of agents with consideration on the overall p…

Decision Making Fairness Sequential Decision Making