通过特征分布自适应，让联邦学习在数据少时也能个性化建模。
Personalized Federated Learning via Feature Distribution Adaptation
- 把表示学习看作生成建模，用全局特征分布训练分类器。
- 在数据稀缺场景下，性能超越当前最优方法。
- 适合资源有限、数据异构的个性化联邦学习应用。
联邦学习（FL）是一种分布式学习框架，利用分布式客户端数据集间的共性来训练全局模型。然而，在客户端异构的情况下，FL 可能无法产生稳定训练结果。个性化联邦学习（PFL）旨在通过为每个客户端学习专属模型来解决此问题。一种方法是将模型训练分解为共享表示学习和个性化分类器训练。然而，以往工作在分类器学习中难以平衡偏差-方差权衡，仅依赖有限本地数据或引入昂贵技术以提升泛化能力。本文将表示学习视为生成建模任务，基于全局特征分布训练分类器。我们提出 pFedFDA 算法，通过将全局生成分类器适配至本地特征分布，高效生成个性化模型。在多个计算机视觉基准测试中，我们的方法在复杂分布偏移下表现优异，尤其在数据稀缺场景中显著优于现有最先进方法。
原文摘要 · Abstract (English)
Federated learning (FL) is a distributed learning framework that leverages commonalities between distributed client datasets to train a global model. Under heterogeneous clients, however, FL can fail to produce stable training results. Personalized federated learning (PFL) seeks to address this by learning individual models tailored to each client. One approach is to decompose model training into shared representation learning and personalized classifier training. Nonetheless, previous works struggle to navigate the bias-variance trade-off in classifier learning, relying solely on limited local datasets or introducing costly techniques to improve generalization. In this work, we frame representation learning as a generative modeling task, where representations are trained with a classifier based on the global feature distribution. We then propose an algorithm, pFedFDA, that efficiently generates personalized models by adapting global generative classifiers to their local feature distributions. Through extensive computer vision benchmarks, we demonstrate that our method can adjust to complex distribution shifts with significant improvements over current state-of-the-art in data-scarce settings.
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。