all InfoSec news
Approximate Gradient Coding for Privacy-Flexible Federated Learning with Non-IID Data
April 5, 2024, 4:11 a.m. | Okko Makkonen, Sampo Niemel\"a, Camilla Hollanti, Serge Kas Hanna
cs.CR updates on arXiv.org arxiv.org
Abstract: This work focuses on the challenges of non-IID data and stragglers/dropouts in federated learning. We introduce and explore a privacy-flexible paradigm that models parts of the clients' local data as non-private, offering a more versatile and business-oriented perspective on privacy. Within this framework, we propose a data-driven strategy for mitigating the effects of label heterogeneity and client straggling on federated learning. Our solution combines both offline data sharing and approximate gradient coding techniques. Through numerical …
arxiv business challenges clients coding cs.cr cs.dc cs.it cs.lg data federated federated learning framework local math.it non paradigm parts perspective privacy private stat.ml work
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Social Engineer For Reverse Engineering Exploit Study
@ Independent study | Remote
Principal Business Value Consultant
@ Palo Alto Networks | Chicago, IL, United States
Cybersecurity Specialist, Sr. (Container Hardening)
@ Rackner | San Antonio, TX
Penetration Testing Engineer- Remote United States
@ Stanley Black & Decker | Towson MD USA - 701 E Joppa Rd Bg 700
Internal Audit- Compliance & Legal Audit-Dallas-Associate
@ Goldman Sachs | Dallas, Texas, United States
Threat Responder
@ Deepwatch | Remote