Fetching the paper…

Reading the bibliography…

Peer-to-peer Federated Learning on Graphs · Around

2019

Peer-to-peer Federated Learning on Graphs

Lalitha, Anusha, Kilinc, Osman Cihan, Javidi, Tara et al.

Original
PDF
Post on X

Understand

We consider the problem of training a machine learning model over a network of nodes in a fully decentralized framework.

The nodes take a Bayesian-like approach via the introduction of a belief over the model parameter space.
We propose a distributed learning algorithm in which nodes update their belief by aggregate information from their one-hop neighbors to learn a model that best fits the observations over the entire network.
In addition, we also obtain sufficient conditions to ensure that the probability of error is small for every node in the network.

Built on

Reaching a consensus
DeGroot, M. H · 1974
Earlier work this paper cites.
Belief Consensus and Distributed Hypothesis Testing in Sensor Networks
Olfati-Saber, R., Franco, E., Frazzoli, E., and Shamma, J. S · 2005
Earlier work this paper cites.
Information Heterogeneity and the Speed of Learning in Social Networks
Jadbabaie, A., Molavi, P., and Tahbaz-salehi, A · 2013
Earlier work this paper cites.
Weight Uncertainty in Neural Networks
Blundell, C., Cornebise, J., Kavukcuoglu, K., and Wierstra, D · 2015
Earlier work this paper cites.

Similar

Non-asymptotic Convergence Rates for Cooperative Learning over Time-varying Directed Graphs
Nedić, A., Olshevsky, A., and Uribe, C. A · 2015
Cited alongside, same era.
Distributed Detection: Finite-Time Analysis and Impact of Network Topology
Shahrampour, S., Rakhlin, A., and Jadbabaie, A · 2015
Cited alongside, same era.
Uncertainty in Deep Learning
Gal, Y · 2016
Cited alongside, same era.
Federated Learning: Strategies for Improving Communication Efficiency
Original
Konečnỳ, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., and Bacon, D · 2016
Cited alongside, same era.

Then

Learning via Active Hypothesis Testing over Networks
Lalitha, A. and Javidi, T · 2017
Later among the works it cites.
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A · 2017
Later among the works it cites.
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., and Vollgraf, R · 2017
Later among the works it cites.
Social Learning and Distributed Hypothesis Testing
Lalitha, A., Javidi, T., and Sarwate, A. D · 2018
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…