Distributed Training of Graph Convolutional Networks

TL;DR

This paper introduces a novel fully-distributed framework for training graph convolutional networks that leverages relational data structures and communication topology optimization, with proven convergence and validated results.

Contribution

It presents the first distributed training algorithm for GCNs, integrating data structure exploitation, convergence guarantees, and communication topology design.

Findings

Distributed GCN training is feasible with convergence guarantees.

The method effectively exploits relational data structures.

Numerical results validate the approach's effectiveness.

Abstract

The aim of this work is to develop a fully-distributed algorithmic framework for training graph convolutional networks (GCNs). The proposed method is able to exploit the meaningful relational structure of the input data, which are collected by a set of agents that communicate over a sparse network topology. After formulating the centralized GCN training problem, we first show how to make inference in a distributed scenario where the underlying data graph is split among different agents. Then, we propose a distributed gradient descent procedure to solve the GCN training problem. The resulting model distributes computation along three lines: during inference, during back-propagation, and during optimization. Convergence to stationary solutions of the GCN training problem is also established under mild conditions. Finally, we propose an optimization criterion to design the communication topology between agents in order to match with the graph describing data relationships. A wide set of numerical results validate our proposal. To the best of our knowledge, this is the first work combining graph convolutional neural networks with distributed optimization.