arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.09568cs.LGcs.CRcs.DC
收藏

FedNet2Net:在具有模型增长的联邦学习中节省通信和计算

FedNet2Net: Saving Communication and Computations in Federated Learning with Model Growing

University of Maryland(马里兰大学)

Amit Kumar Kundu, Joseph Jaja

摘要:

联邦学习(Federated learning,FL)是机器学习的一个新发展的领域,它利用大量分布式客户端的私有数据,在中央服务器的协调下开发一个全局模型,而不显式地暴露数据。标准的FL策略有许多显著的瓶颈,包括大量的沟通需求和对客户资源的高影响。文献中描述了试图解决这些问题的几种策略。在本文中,一个新的方案的基础上的概念“模型生长”的建议。最初,服务器部署一个低复杂度的小模型,该模型经过训练以捕获初始轮集期间的数据复杂度。当这样的模型的性能饱和时,服务器在功能保持转换的帮助下切换到更大的模型。随着客户端处理更多数据,模型复杂性会增加,整个过程会继续,直到达到所需的性能。因此,在我们的方法中,最复杂的模型仅在最后阶段广播,从而大大降低了通信成本和客户端计算需求。所提出的方法进行了广泛的测试,在三个标准的基准,并实现大幅减少通信和客户端的计算,同时实现可比的准确性相比,目前最有效的策略。

英文摘要:

Federated learning (FL) is a recently developed area of machine learning, in which the private data of a large number of distributed clients is used to develop a global model under the coordination of a central server without explicitly exposing the data. The standard FL strategy has a number of significant bottlenecks including large communication requirements and high impact on the clients' resources. Several strategies have been described in the literature trying to address these issues. In this paper, a novel scheme based on the notion of "model growing" is proposed. Initially, the server deploys a small model of low complexity, which is trained to capture the data complexity during the initial set of rounds. When the performance of such a model saturates, the server switches to a larger model with the help of function-preserving transformations. The model complexity increases as more data is processed by the clients, and the overall process continues until the desired performance is achieved. Therefore, the most complex model is broadcast only at the final stage in our approach resulting in substantial reduction in communication cost and client computational requirements. The proposed approach is tested extensively on three standard benchmarks and is shown to achieve substantial reduction in communication and client computation while achieving comparable accuracy when compared to the current most effective strategies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑