用通用去重技术压缩联邦学习模型更新，大幅降低通信开销。
MUFFLe: Efficient Model Update Compression via Generalized Deduplication for Federated Learning
- 通过通用去重在更新向量中消除重复模式，实现可变数量的固定率压缩。
- 20个客户端在IID MNIST上仅需38MB上传量即达92.93%准确率。
- 适合资源受限的边缘联邦学习场景，尤其关注通信效率的研究者。
联邦学习适用于边缘环境，但常受模型更新上传成本限制。本工作进展论文提出MUFFLe，一种将通用去重（GD）融入FedAvg流程的通信高效更新压缩方案。MUFFLe在更新向量中去重重复模式，实现固定率、可变数量的压缩。在20个客户端的IID MNIST实验中，MUFFLe以38MB累计上行通信量达到92.93%的目标准确率，优于8位量化（75MB）、Top-k稀疏化（86MB）和未压缩的FedAvg（310MB）。结果表明，将GD应用于通信高效的联邦学习具有可行性。
原文摘要 · Abstract (English)
Federated learning is well suited to edge environments but is often limited by the uplink cost of transmitting model updates. This Work-in-Progress paper presents MUFFLe, a communication-efficient update compression scheme that integrates generalized deduplication (GD) into the FedAvg pipeline. MUFFLe deduplicates repeated patterns across the update vector, yielding a fixed-rate, variable-count compression scheme. Preliminary experiments on IID MNIST with 20 clients show that MUFFLe reaches the target accuracy of $92.93\%$ with 38~MB cumulative uplink communication, compared with 75~MB for 8-bit quantization, 86~MB for Top-$k$ sparsification, and 310~MB for uncompressed FedAvg. These results demonstrate the feasibility of applying GD to communication-efficient federated learning.
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。