为混合异构数据设计个性化原型学习，提升联邦学习收敛性与通信效率
Personalized federated prototype learning in mixed heterogeneous data scenarios
- 为每个客户端构建个性化无偏原型，融合域知识增强模型表达
- 引入一致性正则化，使本地样本对齐个性化原型，损失函数更快收敛
- 在Digits和Office Caltech上验证有效，显著降低通信开销
联邦学习因其能够同时保护用户隐私并利用多设备分布式数据进行模型训练而受到广泛关注。然而，传统方法通常仅关注孤立的异构场景，导致特征分布或标签分布偏差。实际上，数据异构性是提升模型性能的关键因素。为此，我们提出一种新型方法PFPL，适用于混合异构场景。该方法通过为每个客户端构建个性化、无偏的原型，提供更丰富的域知识与无偏收敛目标。此外，在本地更新阶段引入一致性正则化，使本地实例与其个性化原型对齐，显著提升损失函数的收敛速度。在Digits和Office Caltech数据集上的实验结果验证了该方法的有效性，并成功降低了通信成本。
原文摘要 · Abstract (English)
Federated learning has received significant attention for its ability to simultaneously protect customer privacy and leverage distributed data from multiple devices for model training. However, conventional approaches often focus on isolated heterogeneous scenarios, resulting in skewed feature distributions or label distributions. Meanwhile, data heterogeneity is actually a key factor in improving model performance. To address this issue, we propose a new approach called PFPL in mixed heterogeneous scenarios. The method provides richer domain knowledge and unbiased convergence targets by constructing personalized, unbiased prototypes for each client. Moreover, in the local update phase, we introduce consistent regularization to align local instances with their personalized prototypes, which significantly improves the convergence of the loss function. Experimental results on Digits and Office Caltech datasets validate the effectiveness of our approach and successfully reduce the 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。