提出全权重聚合方法Moss，提升异构设备联邦学习效率与精度。
Moss: Proxy Model-based Full-Weight Aggregation in Federated Learning with Heterogeneous Models
- 采用全权重聚合策略，整合异构模型所有参数
- 训练速度更快，设备耗时和能耗显著降低
- 适合资源受限的移动端联邦学习场景
现代联邦学习在处理高度异构的移动设备中日益重要。现有方法多采用部分模型聚合范式，导致模型精度不足且训练开销较高。本文挑战了当前流行的局部聚合理念，提出一种名为Moss的新方法——全权重聚合，通过整合异构模型中的全部权重，保留更完整的知识。在多种应用场景下的评估表明，与现有最优基线相比，Moss能显著加速训练过程，降低设备端训练时间与能耗，提升模型精度，并减少网络带宽使用。
原文摘要 · Abstract (English)
Modern Federated Learning (FL) has become increasingly essential for handling highly heterogeneous mobile devices. Current approaches adopt a partial model aggregation paradigm that leads to sub-optimal model accuracy and higher training overhead. In this paper, we challenge the prevailing notion of partial-model aggregation and propose a novel "full-weight aggregation" method named Moss, which aggregates all weights within heterogeneous models to preserve comprehensive knowledge. Evaluation across various applications demonstrates that Moss significantly accelerates training, reduces on-device training time and energy consumption, enhances accuracy, and minimizes network bandwidth utilization when compared to state-of-the-art baselines.
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。