Toward a Sustainable Federated Learning Ecosystem: A Practical Least Core Mechanism for Payoff Allocation

2026-02-03

AI Summary

This work addresses the lack of fair and stable incentive mechanisms in federated learning, which undermines the sustainability of long-term collaboration. Drawing on the Least Core concept from cooperative game theory, the authors propose a novel allocation mechanism that prioritizes coalition stability by minimizing the maximum dissatisfaction across all possible sub-coalitions, thereby effectively discouraging participant defection. To overcome the high computational complexity traditionally associated with the Least Core, they introduce a stack-based pruning algorithm that enables efficient and accurate computation even in large-scale federated networks. Experimental results in a federated intrusion detection setting demonstrate that the method precisely identifies key contributors and strategic coalitions, significantly enhancing collaborative stability and offering both theoretical and algorithmic foundations for building sustainable federated learning ecosystems.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Cooperative Game Theory

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Emerging network paradigms and applications increasingly rely on federated learning (FL) to enable collaborative intelligence while preserving privacy. However, the sustainability of such collaborative environments hinges on a fair and stable payoff allocation mechanism. Focusing on coalition stability, this paper introduces a payoff allocation framework based on the least core (LC) concept. Unlike traditional methods, the LC prioritizes the cohesion of the federation by minimizing the maximum dissatisfaction among all potential subgroups, ensuring that no participant has an incentive to break away. To adapt this game-theoretic concept to practical, large-scale networks, we propose a streamlined implementation with a stack-based pruning algorithm, effectively balancing computational efficiency with allocation precision. Case studies in federated intrusion detection demonstrate that our mechanism correctly identifies pivotal contributors and strategic alliances. The results confirm that the practical LC framework promotes stable collaboration and fosters a sustainable FL ecosystem.

Problem

• Federated Learning
• Payoff Allocation
• Coalition Stability
• Least Core
• Sustainable Collaboration

Innovation

• Least Core
• Federated Learning
• Payoff Allocation
• Coalition Stability
• Stack-based Pruning