FedAPA通过梯度自适应聚合提升异构数据下的个性化联邦学习性能
FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Data
- 服务器端基于梯度动态调整聚合权重，实现个性化模型更新
- 在三个数据集上优于10种对比方法，精度更高且计算更高效
- 适合追求高精度与低通信开销的异构数据联邦学习场景
个性化联邦学习（PFL）在保护隐私的同时为客户端独特数据分布定制模型。然而，现有基于聚合权重的PFL方法在异构数据下常面临精度不足、计算效率低和通信开销大的问题。我们提出FedAPA，一种新型PFL方法，采用服务器端、基于梯度的自适应聚合策略，通过集中式更新聚合权重，依据客户端参数变化对聚合权重的梯度进行优化。该方法保证理论收敛性，在三个数据集上相比10种基准方法实现更优精度与计算效率，通信开销具有竞争力。
原文摘要 · Abstract (English)
Personalized federated learning (PFL) tailors models to clients' unique data distributions while preserving privacy. However, existing aggregation-weight-based PFL methods often struggle with heterogeneous data, facing challenges in accuracy, computational efficiency, and communication overhead. We propose FedAPA, a novel PFL method featuring a server-side, gradient-based adaptive aggregation strategy to generate personalized models, by updating aggregation weights based on gradients of client-parameter changes with respect to the aggregation weights in a centralized manner. FedAPA guarantees theoretical convergence and achieves superior accuracy and computational efficiency compared to 10 PFL competitors across three datasets, with competitive communication overhead.
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。