提出动态聚类方法，让联邦学习更好应对数据漂移问题
FedDAA: Dynamic Client Clustering for Concept Drift Adaptation in Federated Learning
- 根据数据漂移类型自动分组客户端，区分真实、虚拟和标签漂移
- 在多个数据集上比现有方法提升7.84%至8.52%准确率
- 适合数据分布随时间变化的现实场景，如医疗或移动设备建模
在联邦学习中，客户端的数据分布可能随时间变化，带来时空异构性，即概念漂移。数据异构性源于三种漂移：真实漂移（条件分布P(y|x)变化）、虚拟漂移（输入分布P(x)变化）和标签漂移（标签分布P(y)变化）。然而，多数现有联邦学习方法仅关注真实漂移。当客户端遭遇虚拟或标签漂移时，这些方法往往无法有选择地保留有用的历史知识，导致灾难性遗忘。关键挑战在于区分不同漂移来源，因其需要不同适应策略：真实漂移需丢弃旧数据，而虚拟或标签漂移则应保留历史数据。未明确识别漂移源会导致通用策略次优，损害泛化能力。为此，我们提出FedDAA，一种动态聚类联邦学习框架，可适应多源概念漂移并保留有价值的历史知识。具体包括三个模块：聚类数量确定模块、真实漂移检测模块和概念漂移适应模块。我们提供了理论收敛保证，实验表明，在Fashion-MNIST、CIFAR-10和CIFAR-100上，相比最先进方法，准确率提升7.84%至8.52%。
原文摘要 · Abstract (English)
In federated learning (FL), the data distribution of each client may change over time, introducing both temporal and spatial data heterogeneity, known as concept drift. Data heterogeneity arises from three drift sources: real drift (a shift in the conditional distribution P(y|x)), virtual drift (a shift in the input distribution P(x)), and label drift (a shift in the label distribution P(y)). However, most existing FL methods addressing concept drift primarily focus on real drift. When clients experience virtual or label drift, these methods often fail to selectively retain useful historical knowledge, leading to catastrophic forgetting. A key challenge lies in distinguishing different sources of drift, as they require distinct adaptation strategies: real drift calls for discarding outdated data, while virtual or label drift benefits from retaining historical data. Without explicitly identifying the drift sources, a general adaptation strategy is suboptimal and may harm generalization. To address this challenge, we propose FedDAA, a dynamic clustered FL framework designed to adapt to multi-source concept drift while preserving valuable historical knowledge. Specifically, FedDAA integrates three modules: a cluster number determination module to find the optimal number of clusters; a real drift detection module to distinguish real drift from virtual/label drift; and a concept drift adaptation module to adapt to new data while retaining useful historical information. We provide theoretical convergence guarantees, and experiments show that FedDAA achieves 7.84% to 8.52% accuracy improvements over state-of-the-art methods on Fashion-MNIST, CIFAR-10, and CIFAR-100.
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。