Privacy-Preserving Distributed Nonnegative Matrix Factorization

arXiv:2403.18326v1 Announce Type: cross
Abstract: Nonnegative matrix factorization (NMF) is an effective data representation tool with numerous applications in signal processing and machine learning. However, deploying NMF in a decentralized manner over ad-hoc networks introduces privacy concerns due to the conventional approach of sharing raw data among network agents. To address this, we propose a privacy-preserving algorithm for fully-distributed NMF that decomposes a distributed large data matrix into left and right matrix factors while safeguarding each agent's local data privacy. …

abstract agents applications arxiv concerns cs.cr cs.dc cs.lg data decentralized distributed eess.sp factorization however machine machine learning matrix network networks privacy processing raw representation signal tool type