用博弈论设计去中心化联邦学习，解决动态网络下的模型收敛难题。
pFedGame -- Decentralized Federated Learning using Game Theory in Dynamic Topology
- 基于博弈论设计双人零和合作游戏，实现无中心服务器的聚合。
- 在异构数据下实验准确率超70%，克服动态拓扑中的梯度消失问题。
- 适合高动态、低信任的分布式场景，如物联网与隐私敏感应用。
传统联邦学习框架面临中心化聚合服务器性能瓶颈、数据偏差、模型收敛差及模型中毒攻击风险，且对中心化基础设施信任度低。本文提出一种基于博弈论的去中心化联邦学习方法 pFedGame，适用于时间动态网络。该算法无需中心服务器，在每轮联邦学习中分两步进行：首先选择合适的协作同伴，其次通过双人零和合作博弈，采用最优联邦学习聚合策略实现收敛。实验表明，pFedGame 在异构数据下表现优异，准确率超过70%，有效缓解了动态拓扑中的梯度消失与收敛困难问题。
原文摘要 · Abstract (English)
Conventional federated learning frameworks suffer from several challenges including performance bottlenecks at the central aggregation server, data bias, poor model convergence, and exposure to model poisoning attacks, and limited trust in the centralized infrastructure. In the current paper, a novel game theory-based approach called pFedGame is proposed for decentralized federated learning, best suitable for temporally dynamic networks. The proposed algorithm works without any centralized server for aggregation and incorporates the problem of vanishing gradients and poor convergence over temporally dynamic topology among federated learning participants. The solution comprises two sequential steps in every federated learning round, for every participant. First, it selects suitable peers for collaboration in federated learning. Secondly, it executes a two-player constant sum cooperative game to reach convergence by applying an optimal federated learning aggregation strategy. Experiments performed to assess the performance of pFedGame in comparison to existing methods in decentralized federated learning have shown promising results with accuracy higher than 70% for heterogeneous data.
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。