Timezone: »

 
Poster
Bayesian Nonparametric Federated Learning of Neural Networks
Mikhail Yurochkin · Mayank Agarwal · Soumya Ghosh · Kristjan Greenewald · Nghia Hoang · Yasaman Khazaeni

Wed Jun 12 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #20
in Posters Wed »

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric framework for federated learning with neural networks. Each data server is assumed to provide local neural network weights, which are modeled through our framework. We then develop an inference approach that allows us to synthesize a more expressive global network without additional supervision, data pooling and with as few as a single communication round. We then demonstrate the efficacy of our approach on federated learning problems simulated from two popular image classification datasets.

Keywords: Bayesian Deep Learning · Bayesian Nonparametrics · Parallel and Distributed Learning

Author Information

Mikhail Yurochkin (IBM Research AI)
Mayank Agarwal (IBM Research)
Soumya Ghosh (IBM Research)
Kristjan Greenewald (IBM)
Nghia Hoang (MIT-IBM Watson AI Lab, IBM Research)
Yasaman Khazaeni (IBM Research)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors