用反馈对齐缓解联邦学习中的数据异构问题，提升模型收敛性。
Federated Learning with Feedback Alignment
- 用全局模型权重作为反向传播的反馈矩阵，实现本地更新对齐。
- 实验显示可有效降低局部漂移，提升模型准确率与收敛稳定性。
- 无需额外通信开销，适配现有联邦学习框架，易集成使用。
联邦学习（FL）可在保护数据隐私的前提下实现多客户端协作训练，但面临数据异构（non-IID）问题，导致局部漂移，阻碍全局模型收敛。为此，我们提出联邦学习反馈对齐（FLFA）框架，将反馈对齐机制引入联邦学习。FLFA在本地训练的反向传播中，使用全局模型权重作为共享反馈矩阵，使本地更新与全局模型高效对齐。该方法以极小的计算开销和无额外通信成本，缓解局部漂移。理论分析表明其能有效抑制局部漂移并保证局部与全局模型的稳健收敛。实证评估通过准确率对比和局部漂移测量，验证了FLFA能显著提升其他联邦学习方法的性能，展现出强有效性。
原文摘要 · Abstract (English)
Federated Learning (FL) enables collaborative training across multiple clients while preserving data privacy, yet it struggles with data heterogeneity, where clients' data are not distributed independently and identically (non-IID). This causes local drift, hindering global model convergence. To address this, we introduce Federated Learning with Feedback Alignment (FLFA), a novel framework that integrates feedback alignment into FL. FLFA uses the global model's weights as a shared feedback matrix during local training's backward pass, aligning local updates with the global model efficiently. This approach mitigates local drift with minimal additional computational cost and no extra communication overhead. Our theoretical analysis supports FLFA's design by showing how it alleviates local drift and demonstrates robust convergence for both local and global models. Empirical evaluations, including accuracy comparisons and measurements of local drift, further illustrate that FLFA can enhance other FL methods demonstrating its effectiveness.
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。