IGLU: Efficient GCN Training via Lazy Updates
This addresses the computational bottleneck in GCN training for graph-based machine learning applications, offering a significant efficiency improvement.
The paper tackles the problem of inefficient training of multi-layer Graph Convolution Networks (GCNs) by proposing the IGLU method, which uses lazy updates to reduce compute costs, resulting in up to 1.2% better accuracy and up to 88% less compute in benchmark experiments.
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.