IGLU: Efficient GCN Training via Lazy Updates

Abstract

Training multi-layer Graph Convolution Networks (GCN) using standard SGD techniques scales poorly as each descent step ends up updating node embeddings for a large portion of the graph. Recent attempts to remedy this sub-sample the graph that reduces compute but introduce additional variance and may offer suboptimal performance. This paper develops the IGLU method that caches intermediate computations at various GCN layers thus enabling lazy updates that significantly reduce the compute cost of descent. IGLU introduces bounded bias into the gradients but nevertheless converges to a first-order saddle point under standard assumptions such as objective smoothness. Benchmark experiments show that IGLU offers up to 1.2% better accuracy despite requiring up to 88% less compute.

arXiv commentPublished as Conference Paper at ICLR 2022, 36 Pages

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Semi-Supervised Classification with Graph Convolutional Networks
• Spectral Networks and Locally Connected Networks on Graphs
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Adaptive Sampling Towards Fast Graph Representation Learning
• Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks
• Graph-based, Self-Supervised Program Repair from Diagnostic Feedback