发表机构
Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT); Vietnam National University Ho Chi Minh City; School of Mathematics, University of Birmingham; School of Computing, Engineering and Digital Technologies, Teesside University（胡志明市技术大学计算机科学与工程学院; 越南国家大学胡志明市分校; 伯明翰大学数学学院; 提赛德大学计算、工程与数字技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对基于格的去中心化联邦学习的机会主义行为，本文提出结合有限理性、收益矩阵与声誉奖惩机制的演化博弈框架，仿真显示其在准确率、合作频率等指标上显著优于基线。
AI 中文摘要
去中心化联邦学习（Decentralized Federated Learning，DFL）已成为最优的隐私保护解决方案，但由于缺乏中央协调器，它仍易受机会主义行为影响。演化博弈论（Evolutionary Game Theory，EGT）是分析此类行为的强大框架，不过现有研究常假设智能体具有完全理性且策略固定。为解决这些局限，本文提出一种新颖的EGT框架，用于分析策略演化并提升整体系统性能。本文主要贡献有三：其一，在有限理性假设下，对格网络结构上的点对点（Peer-to-Peer，P2P）交互进行建模；其二，构建包含训练成本、通信开销与合作奖励的综合收益矩阵，同时定制策略更新规则以捕捉空间传播动态；其三，融入基于声誉的奖惩机制，有效遏制搭便车行为。仿真结果显示，该框架显著优于基线：平均准确率从约70%提升至82%，合作频率接近100%（基线低于5%），准确率方差从约0.40降至0.002，从而加快均匀收敛并保障系统稳定性。
英文摘要
Decentralized Federated Learning (DFL) has emerged as an optimal privacy-preserving solution; however, it remains vulnerable to opportunistic behaviors due to the absence of a central coordinator. While Evolutionary Game Theory (EGT) serves as a powerful framework for analyzing such behaviors, existing studies often assume that agents possess perfect rationality and maintain static strategies. To address these limitations, this paper proposes a novel EGT framework designed to analyze strategic evolution and enhance overall system performance. The primary contributions of this work are threefold: First, we model peer-to-peer (P2P) interactions on a lattice network structure under the assumption of bounded rationality. Second, we formulate a comprehensive payoff matrix incorporating training costs, communication overhead, and cooperative rewards, while tailoring a strategy update rule that captures spatial propagation dynamics. Third, we integrate a reputation-based reward-and-punishment mechanism to effectively deter free-riding behaviors. Simulation results demonstrate that the framework significantly outperforms the baseline. Specifically, it increases average accuracy from approximately 70% to 82%, elevates cooperation frequency to approach 100% (compared to below 5% in the baseline), and drops accuracy variance from around 0.40 to 0.002, thereby accelerating uniform convergence and ensuring system stability.
