FedBWO通过只传性能分数而非模型权重，大幅降低联邦学习通信开销。
FedBWO: Enhancing Communication Efficiency in Federated Learning
- 客户端仅上传性能评分，不传输模型权重，减少通信量。
- 相比FedAvg提升平均21%准确率，相比FedGWO提升12%。
- 适合资源受限设备的高效联邦学习，尤其适用于低带宽场景。
联邦学习（FL）是一种分布式机器学习框架，客户端在保护数据隐私的前提下，使用本地数据协同训练共享模型。然而，受限于设备资源，客户端常面临传输能力不足的问题。现有方法在训练过程中传输大量模型权重，需高通信带宽，当客户端数量增加时易形成瓶颈。本文提出联邦黑寡妇优化（FedBWO）方法，通过仅传输性能评分替代本地模型权重，显著减少通信开销。该方法利用黑寡妇优化（BWO）算法改进本地模型更新。实验表明，FedBWO在全局模型性能和通信效率方面均有显著提升：相比FedAvg，平均准确率提高21%；相比FedGWO，提升12%。同时，通信成本大幅降低。
原文摘要 · Abstract (English)
Federated Learning (FL) is a distributed Machine Learning (ML) setup, where a shared model is collaboratively trained by various clients using their local datasets while keeping the data private. Considering resource-constrained devices, FL clients often suffer from restricted transmission capacity. Aiming to enhance the system performance, the communication between clients and server needs to be diminished. Current FL strategies transmit a tremendous amount of data (model weights) within the FL process, which needs a high communication bandwidth. Considering resource constraints, increasing the number of clients and, consequently, the amount of data (model weights) can lead to a bottleneck. In this paper, we introduce the Federated Black Widow Optimization (FedBWO) technique to decrease the amount of transmitted data by transmitting only a performance score rather than the local model weights from clients. FedBWO employs the BWO algorithm to improve local model updates. The conducted experiments prove that FedBWO remarkably improves the performance of the global model and the communication efficiency of the overall system. According to the experimental outcomes, FedBWO enhances the global model accuracy by an average of 21% over FedAvg, and 12% over FedGWO. Furthermore, FedBWO dramatically decreases the communication cost compared to other methods.
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。