all InfoSec news
Adaptive Coded Federated Learning: Privacy Preservation and Straggler Mitigation
March 25, 2024, 4:11 a.m. | Chengxi Li, Ming Xiao, Mikael Skoglund
cs.CR updates on arXiv.org arxiv.org
Abstract: In this article, we address the problem of federated learning in the presence of stragglers. For this problem, a coded federated learning framework has been proposed, where the central server aggregates gradients received from the non-stragglers and gradient computed from a privacy-preservation global coded dataset to mitigate the negative impact of the stragglers. However, when aggregating these gradients, fixed weights are consistently applied across iterations, neglecting the generation process of the global coded dataset and …
address article arxiv cs.cr cs.lg dataset eess.sp federated federated learning framework global mitigation non presence preservation privacy problem server
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Threat Analysis Engineer
@ Gen | IND - Tamil Nadu, Chennai
Head of Security
@ Hippocratic AI | Palo Alto
IT Security Vulnerability Management Specialist (15.10)
@ OCT Consulting, LLC | Washington, District of Columbia, United States
Security Engineer - Netskope/Proofpoint
@ Sainsbury's | Coventry, West Midlands, United Kingdom
Journeyman Cybersecurity Analyst
@ ISYS Technologies | Kirtland AFB, NM, United States