提出端到端压缩流水线，让联邦学习在低带宽下更快更省资源。
A Full Compression Pipeline for Green Federated Learning in Communication-Constrained Environments
- 整合剪枝、量化和哈夫曼编码，统一压缩模型与通信数据。
- 在CIFAR-10上使模型大小缩小11倍，精度仅降2%，训练快60%以上。
- 适合低带宽、资源受限的联邦学习场景，如边缘设备部署。
联邦学习（FL）可在不共享原始数据的前提下实现跨客户端协同训练，保护隐私。然而，FL常面临显著的通信与计算开销，限制其可扩展性与可持续性。本文提出一种面向通信受限环境的全压缩流水线（FCP），将剪枝、量化和哈夫曼编码三种深度压缩技术整合为统一的端到端框架。通过压缩本地模型与通信数据，FCP大幅降低传输成本与资源消耗，同时保持较高精度。我们构建了一个评估框架，将通信与计算开销统一为模型总成本，实现效率权衡的全面分析。在独立同分布（IID）与非独立同分布（non-IID）数据设置下进行评估。在一项典型场景中，使用10个客户端、2 Mbps带宽训练ResNet-12模型于CIFAR-10数据集，FCP实现模型尺寸超过11倍压缩，精度仅比无压缩基线下降2%，使训练速度提升60%以上。
原文摘要 · Abstract (English)
Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, thereby preserving privacy. However, FL often suffers from significant communication and computational overhead, limiting its scalability and sustainability. In this work, we introduce a Full Compression Pipeline (FCP) for FL in communication-constrained environments. FCP integrates three complementary deep compression techniques (pruning, quantization, and Huffman encoding) into a unified end-to-end framework. By compressing local models and communication payloads, FCP substantially reduces transmission costs and resource consumption while maintaining competitive accuracy. To quantify its impact, we develop an evaluation framework that captures both communication and computation overheads as a unified model cost, allowing a holistic assessment of efficiency trade-offs. The pipeline is evaluated in an independent and identically distributed (IID) and non-IID data setting. In one representative scenario, training a ResNet-12 model on the CIFAR-10 dataset with ten clients and a 2 Mbps bandwidth, the FCP achieves more than 11$\times$ reduction in model size, with only a 2% drop in accuracy compared to the uncompressed baseline. This results in an FL training that is more than 60% faster.
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。