通过分离风格与内容，实现个性化联邦学习的高效通信
Federated style aware transformer aggregation of representations
- 将客户端特征拆分为共享内容和个性风格，用Transformer加权聚合原型
- 在不增加通信成本下，提升异构环境下的个性化性能与鲁棒性
- 适合数据分布差异大、通信受限的边缘设备场景
个性化联邦学习（PFL）面临来自多样化客户端数据的领域异质性、参与偏斜导致的数据不平衡以及严格的通信约束等持续挑战。传统联邦学习常缺乏个性化能力，单一全局模型难以捕捉客户端特异性，导致预测偏差和泛化能力下降，尤其在数据分布高度偏离的客户端上表现更差。为此，我们提出FedSTAR，一种风格感知的联邦学习框架，通过将客户端特定风格因子从共享内容表示中解耦。该框架利用基于Transformer的注意力机制对类别原型进行聚合，使服务器能自适应地加权客户端贡献，同时保留个性化能力。此外，通过交换紧凑的原型和风格向量而非完整模型参数，显著降低通信开销。实验表明，在不增加通信成本的前提下，结合内容-风格解耦与注意力驱动的原型聚合，可有效提升异构环境中的个性化与鲁棒性。
原文摘要 · Abstract (English)
Personalized Federated Learning (PFL) faces persistent challenges, including domain heterogeneity from diverse client data, data imbalance due to skewed participation, and strict communication constraints. Traditional federated learning often lacks personalization, as a single global model cannot capture client-specific characteristics, leading to biased predictions and poor generalization, especially for clients with highly divergent data distributions. To address these issues, we propose FedSTAR, a style-aware federated learning framework that disentangles client-specific style factors from shared content representations. FedSTAR aggregates class-wise prototypes using a Transformer-based attention mechanism, allowing the server to adaptively weight client contributions while preserving personalization. Furthermore, by exchanging compact prototypes and style vectors instead of full model parameters, FedSTAR significantly reduces communication overhead. Experimental results demonstrate that combining content-style disentanglement with attention-driven prototype aggregation improves personalization and robustness in heterogeneous environments without increasing communication cost.
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。