Decentralized Collaborative Learning of Personalized Models over Networks
ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 54(2017)
摘要
We 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. To optimize this challenging objective, our decentralized algorithm is based on ADMM.
更多查看译文
关键词
personalized models,networks,learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络