Section: New Results

Decentralized Learning and Privacy

In [15] 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.

In subsequent work in collaboration with Rachid Guerraoui's group at EPFL [18], we study how agents can collaborate to improve upon their locally learned model without leaking sensitive information about their data. Our first contribution is to reformulate this problem so that it can be solved by a block coordinate descent algorithm. We obtain an efficient and fully decentralized protocol working in an asynchronous fashion. Our second contribution is to make our algorithm differentially private to protect against the disclosure of any information about personal datasets. We prove convergence rates and exhibit the trade-off between utility and privacy. Our experiments show that our approach dramatically outperforms previous work in the non-private case, and that under privacy constraints we significantly improve over purely local models. A preliminary version of this work was presented at the NIPS 2017 workshop on machine Learning on the Phone and other Consumer Devices [16].