Web: http://arxiv.org/abs/2201.08459

Jan. 24, 2022, 2:10 a.m. | Or Litany, Haggai Maron, David Acuna, Jan Kautz, Gal Chechik, Sanja Fidler

cs.LG updates on arXiv.org arxiv.org

Standard Federated Learning (FL) techniques are limited to clients with
identical network architectures. This restricts potential use-cases like
cross-platform training or inter-organizational collaboration when both data
privacy and architectural proprietary are required. We propose a new FL
framework that accommodates heterogeneous client architecture by adopting a
graph hypernetwork for parameter sharing. A property of the graph hyper network
is that it can adapt to various computational graphs, thereby allowing
meaningful parameter sharing across models. Unlike existing solutions, our
framework does …

arxiv federated learning graph learning

More from arxiv.org / cs.LG updates on arXiv.org

Director, Data Engineering and Architecture

@ Chainalysis | California | New York | Washington DC | Remote - USA

Deep Learning Researcher

@ Topaz Labs | Dallas, TX

Sr Data Engineer (Contractor)

@ SADA | US - West

Senior Cloud Database Administrator

@ Findhelp | Remote

Senior Data Analyst

@ System1 | Remote

Speech Machine Learning Research Engineer

@ Samsung Research America | Mountain View, CA