The reviewed record of science sign in
Pith

arxiv: 2105.03591 · v1 · pith:5SLIYE4K · submitted 2021-05-08 · cs.LG · cs.AI· cs.NI

Loss Tolerant Federated Learning

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:5SLIYE4Krecord.jsonopen to challenge →

classification cs.LG cs.AIcs.NI
keywords federatedlearninglosspacketbeenclientdatadevices
0
0 comments X
read the original abstract

Federated learning has attracted attention in recent years for collaboratively training data on distributed devices with privacy-preservation. The limited network capacity of mobile and IoT devices has been seen as one of the major challenges for cross-device federated learning. Recent solutions have been focusing on threshold-based client selection schemes to guarantee the communication efficiency. However, we find this approach can cause biased client selection and results in deteriorated performance. Moreover, we find that the challenge of network limit may be overstated in some cases and the packet loss is not always harmful. In this paper, we explore the loss tolerant federated learning (LT-FL) in terms of aggregation, fairness, and personalization. We use ThrowRightAway (TRA) to accelerate the data uploading for low-bandwidth-devices by intentionally ignoring some packet losses. The results suggest that, with proper integration, TRA and other algorithms can together guarantee the personalization and fairness performance in the face of packet loss below a certain fraction (10%-30%).

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.