Large-scale graph representation learning with very deep GNNs and self-supervision
This addresses the problem of scalable graph representation learning for researchers and practitioners, showing incremental progress by applying deep GNNs and self-supervision to established benchmarks.
The paper tackled the challenge of scaling graph neural networks (GNNs) to large datasets, achieving top-3 performance on the MAG240M and PCQM4M benchmarks in the Open Graph Benchmark Large-Scale Challenge.
Effectively and efficiently deploying graph neural networks (GNNs) at scale remains one of the most challenging aspects of graph representation learning. Many powerful solutions have only ever been validated on comparatively small datasets, often with counter-intuitive outcomes -- a barrier which has been broken by the Open Graph Benchmark Large-Scale Challenge (OGB-LSC). We entered the OGB-LSC with two large-scale GNNs: a deep transductive node classifier powered by bootstrapping, and a very deep (up to 50-layer) inductive graph regressor regularised by denoising objectives. Our models achieved an award-level (top-3) performance on both the MAG240M and PCQM4M benchmarks. In doing so, we demonstrate evidence of scalable self-supervised graph representation learning, and utility of very deep GNNs -- both very important open issues. Our code is publicly available at: https://github.com/deepmind/deepmind-research/tree/master/ogb_lsc.