Fair and efficient contribution valuation for vertical federated learning

01/07/2022
by   Zhenan Fan, et al.
0

Federated learning is a popular technology for training machine learning models on distributed data sources without sharing data. Vertical federated learning or feature-based federated learning applies to the cases that different data sources share the same sample ID space but differ in feature space. To ensure the data owners' long-term engagement, it is critical to objectively assess the contribution from each data source and recompense them accordingly. The Shapley value (SV) is a provably fair contribution valuation metric originated from cooperative game theory. However, computing the SV requires extensively retraining the model on each subset of data sources, which causes prohibitively high communication costs in federated learning. We propose a contribution valuation metric called vertical federated Shapley value (VerFedSV) based on SV. We show that VerFedSV not only satisfies many desirable properties for fairness but is also efficient to compute, and can be adapted to both synchronous and asynchronous vertical federated learning algorithms. Both theoretical analysis and extensive experimental results verify the fairness, efficiency, and adaptability of VerFedSV.

READ FULL TEXT
research
09/14/2020

A Principled Approach to Data Valuation for Federated Learning

Federated learning (FL) is a popular technique to train machine learning...
research
04/16/2020

Asymmetrical Vertical Federated Learning

Federated learning is a distributed machine learning method that aims to...
research
09/17/2021

Achieving Model Fairness in Vertical Federated Learning

Vertical federated learning (VFL), which enables multiple enterprises po...
research
10/17/2022

Private Data Valuation and Fair Payment in Data Marketplaces

Data valuation is an essential task in a data marketplace. It aims at fa...
research
09/19/2021

Improving Fairness for Data Valuation in Federated Learning

Federated learning is an emerging decentralized machine learning scheme ...
research
11/30/2018

LoAdaBoost:Loss-Based AdaBoost Federated Machine Learning on medical Data

Medical data are valuable for improvement of health care, policy making ...
research
04/16/2020

Asymmetrically Vertical Federated Learning

Federated learning is a distributed machine learning method that aims to...

Please sign up or login with your details

Forgot password? Click here to reset