通过低秩近似与量化压缩梯度，大幅降低联邦学习通信开销。
Quantized Rank Reduction: A Communications-Efficient Federated Learning Scheme for Network-Critical Applications
- 用低秩近似和量化压缩模型更新梯度
- 通信量显著下降，精度损失极小
- 适合对带宽敏感的网络关键场景
联邦学习允许多个设备在不交换原始数据的前提下协同训练共享模型，保护用户隐私与安全。各设备在本地训练模型并仅上传模型更新，但频繁的模型参数交换带来巨大通信开销。本文提出一种通信高效的联邦学习方案，通过神经网络梯度的低秩近似与量化技术，显著降低去中心化学习过程中的网络负载，同时对模型精度影响极小。
原文摘要 · Abstract (English)
Federated learning is a machine learning approach that enables multiple devices (i.e., agents) to train a shared model cooperatively without exchanging raw data. This technique keeps data localized on user devices, ensuring privacy and security, while each agent trains the model on their own data and only shares model updates. The communication overhead is a significant challenge due to the frequent exchange of model updates between the agents and the central server. In this paper, we propose a communication-efficient federated learning scheme that utilizes low-rank approximation of neural network gradients and quantization to significantly reduce the network load of the decentralized learning process with minimal impact on the model's accuracy.
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。