解决联邦学习中数据异构导致的特征对齐问题，提升模型泛化能力。
Enhancing Federated Quadruplet Learning: Stochastic Client Selection and Embedding Stability Analysis
- 通过最小化同类样本距离、最大化异类样本距离，优化特征表示。
- 在CIFAR-10/100和Tiny-ImageNet上均优于现有基线，提升显著。
- 适用于数据不平衡、客户端数量少的联邦学习场景。
联邦学习（FL）允许在不集中数据的前提下，在分布式客户端间进行模型训练。然而，由于客户端间存在数据异构性，尤其是在数据量有限和类别不平衡的情况下，全局模型的泛化性能通常会下降。为此，我们提出FedQuad，一种新方法，明确要求最小化同类样本的表示距离，同时促进异类样本在客户端间的分离。通过联合最小化正样本对的距离并最大化负样本对的距离，该方法缓解了模型聚合过程中引入的表示错位问题。我们在CIFAR-10、CIFAR-100和Tiny-ImageNet上，在多种非独立同分布（non-IID）设置及不同客户端数量下评估了该方法，结果表明其在多个基准方法上均取得一致改进。此外，我们对集中式与联邦环境中基于度量学习的方法进行了全面分析，强调其在缓解异构数据分布下的表示崩溃问题上的有效性。
原文摘要 · Abstract (English)
Federated Learning (FL) enables decentralised model training across distributed clients without requiring data centralisation. However, the generalisation performance of the global model is usually degraded by data heterogeneity across clients, particularly under limited data availability and class imbalance. To address this challenge, we propose FedQuad, a novel method that explicitly enforces minimising intra-class representations while enabling inter-class splits across clients. By jointly minimising distances between positive pairs and maximising distances between negative pairs, the proposed approach mitigates representation misalignment introduced during model aggregation. We evaluate our method on CIFAR-10, CIFAR-100, and Tiny-ImageNet under diverse non-IID settings and varying numbers of clients, demonstrating consistent improvements over existing baselines. Additionally, we provide a comprehensive analysis of metric learning-based approaches in both centralised and federated environments, highlighting their effectiveness in alleviating representation collapse under heterogeneous data distributions.
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。