arXiv:2602.03387cs.GTcs.AI2026-02

提出一种公平分配机制,让联邦学习各方长期稳定合作。

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

  • 用最小核心概念优化收益分配,防止小组分裂
  • 算法可处理大规模网络,计算效率高且结果准确
  • 适合需要长期协作的隐私保护型智能系统

新兴网络范式与应用越来越多依赖联邦学习(FL)实现协同智能并保护隐私。然而,此类协作环境的可持续性取决于公平稳定的收益分配机制。本文聚焦联盟稳定性,提出基于最小核心(LC)概念的收益分配框架。与传统方法不同,该方法通过最小化所有潜在子群体中的最大不满程度,优先保障联盟凝聚力,确保参与者无动机脱离。为将这一博弈论概念应用于实际大规模网络,我们设计了一种简化实现方案,结合基于栈的剪枝算法,在计算效率与分配精度间取得良好平衡。在联邦入侵检测的案例研究中,该机制能准确识别关键贡献者与战略联盟。结果表明,该实用化的最小核心框架有助于促进稳定协作,构建可持续的联邦学习生态。

原文摘要 · Abstract (English)

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.

联邦学习收益分配博弈论协同智能

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。