Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks

TL;DR

This paper introduces LADIES, a novel layer-dependent importance sampling method for efficient training of large graph convolutional networks, reducing computational costs while improving accuracy.

Contribution

LADIES effectively combines layer-dependent importance sampling with neighborhood selection, outperforming existing methods in efficiency and generalization for large-scale GCN training.

Findings

LADIES reduces training time and memory usage compared to previous sampling methods.

LADIES achieves better generalization accuracy than full-batch GCN.

Theoretically and experimentally validated improvements over prior approaches.

Abstract

Graph convolutional networks (GCNs) have recently received wide attentions, due to their successful applications in different graph tasks and different domains. Training GCNs for a large graph, however, is still a challenge. Original full-batch GCN training requires calculating the representation of all the nodes in the graph per GCN layer, which brings in high computation and memory costs. To alleviate this issue, several sampling-based methods have been proposed to train GCNs on a subset of nodes. Among them, the node-wise neighbor-sampling method recursively samples a fixed number of neighbor nodes, and thus its computation cost suffers from exponential growing neighbor size; while the layer-wise importance-sampling method discards the neighbor-dependent constraints, and thus the nodes sampled across layer suffer from sparse connection problem. To deal with the above two problems, we propose a new effective sampling algorithm called LAyer-Dependent ImportancE Sampling (LADIES). Based on the sampled nodes in the upper layer, LADIES selects their neighborhood nodes, constructs a bipartite subgraph and computes the importance probability accordingly. Then, it samples a fixed number of nodes by the calculated probability, and recursively conducts such procedure per layer to construct the whole computation graph. We prove theoretically and experimentally, that our proposed sampling algorithm outperforms the previous sampling methods in terms of both time and memory costs. Furthermore, LADIES is shown to have better generalization accuracy than original full-batch GCN, due to its stochastic nature.