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 decentralized
Collaborative Graph Learning (CGL) dynamically refining collaboration weights
in a privacy-preserving manner based on local task similarities. Our extensive
experimentation demonstrates the efficacy of MAPL and its competitive (or, in
most cases, superior) performance compared to its centralized model-agnostic
counterparts, without relying on any central server. Our code is available and
can be accessed here: this https URL

在去中心化环境中，有效协作是一个不太被探索的领域。为了解决这个问题，我们引入了模型不可知的点对点学习（简称 MAPL），通过邻近客户之间的点对点通信，同时学习异构个人化模型和协作图。我们的实验证明了 MAPL 的有效性以及与集中式无模型对应方法的竞争性（甚至是卓越）性能，而不依赖于任何中央服务器。