MAPL: Model Agnostic Peer-to-peer Learning

arXiv:2403.19792v1 Announce Type: cross
Abstract: Effective collaboration among heterogeneous clients in a decentralized setting is a rather unexplored avenue in the literature. To structurally address this, we introduce Model Agnostic Peer-to-peer Learning (coined as MAPL) a novel approach to simultaneously learn heterogeneous personalized models as well as a collaboration graph through peer-to-peer communication among neighboring clients. MAPL is comprised of two main modules: (i) local-level Personalized Model Learning (PML), leveraging a combination of intra- and inter-client contrastive losses; (ii) network-wide …

arxiv cs.ai cs.cr cs.dc cs.lg peer-to-peer