Decentralized Collaborative Learning of Personalized Models over Networks
KeywordsComputer Science - Learning
Computer Science - Distributed, Parallel, and Cluster Computing
Computer Science - Systems and Control
Statistics - Machine Learning
Full recordShow full item record
AbstractWe consider a set of learning agents in a collaborative peer-to-peer network, where each agent learns a personalized model according to its own learning objective. The question addressed in this paper is: how can agents improve upon their locally trained model by communicating with other agents that have similar objectives? We introduce and analyze two asynchronous gossip algorithms running in a fully decentralized manner. Our first approach, inspired from label propagation, aims to smooth pre-trained local models over the network while accounting for the confidence that each agent has in its initial model. In our second approach, agents jointly learn and propagate their model by making iterative updates based on both their local dataset and the behavior of their neighbors. Our algorithm to optimize this challenging objective in a decentralized way is based on ADMM.