Social Welfare Maximization in Cross-Silo Federated Learning

TL;DR

This paper models cross-silo federated learning as a public goods game, revealing a social dilemma and proposing a strategy to unilaterally maximize social welfare, validated through experiments.

Contribution

It introduces a novel game-theoretic model for cross-silo FL and applies MMZD strategy to optimize social welfare, addressing free-riding issues.

Findings

Existence of social dilemma in cross-silo FL.

MMZD strategy effectively maximizes social welfare.

Unilateral control of social welfare by individual organizations.

Abstract

As one of the typical settings of Federated Learning (FL), cross-silo FL allows organizations to jointly train an optimal Machine Learning (ML) model. In this case, some organizations may try to obtain the global model without contributing their local training, lowering the social welfare. In this paper, we model the interactions among organizations in cross-silo FL as a public goods game for the first time and theoretically prove that there exists a social dilemma where the maximum social welfare is not achieved in Nash equilibrium. To overcome this social dilemma, we employ the Multi-player Multi-action Zero-Determinant (MMZD) strategy to maximize the social welfare. With the help of the MMZD, an individual organization can unilaterally control the social welfare without extra cost. Experimental results validate that the MMZD strategy is effective in maximizing the social welfare.