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.

翻译：联邦学习非常适合边缘环境，但其性能常受限于传输模型更新的上行链路开销。这篇工作进展论文提出了MUFFLe，一种通信高效的更新压缩方案，它将广义去重（GD）集成到FedAvg流程中。MUFFLe对更新向量中的重复模式进行去重，从而产生一种固定速率、可变计数的压缩方案。基于20个客户端在IID MNIST数据集上的初步实验表明，MUFFLe达到目标准确率$92.93\%$时，累积上行通信量为38~MB，而8位量化需75~MB，Top-$k$稀疏化需86~MB，未压缩FedAvg需310~MB。这些结果证明了将GD应用于通信高效联邦学习的可行性。