Large-Scale Representation Learning on Graphs via Bootstrapping

Abstract

Self-supervised learning provides a promising path towards eliminating the need for costly label information in representation learning on graphs. However, to achieve state-of-the-art performance, methods often need large numbers of negative examples and rely on complex augmentations. This can be prohibitively expensive, especially for large graphs. To address these challenges, we introduce Bootstrapped Graph Latents (BGRL) - a graph representation learning method that learns by predicting alternative augmentations of the input. BGRL uses only simple augmentations and alleviates the need for contrasting with negative examples, and is thus scalable by design. BGRL outperforms or matches prior methods on several established benchmarks, while achieving a 2-10x reduction in memory costs. Furthermore, we show that BGRL can be scaled up to extremely large graphs with hundreds of millions of nodes in the semi-supervised regime - achieving state-of-the-art performance and improving over supervised baselines where representations are shaped only through label information. In particular, our solution centered on BGRL constituted one of the winning entries to the Open Graph Benchmark - Large Scale Challenge at KDD Cup 2021, on a graph orders of magnitudes larger than all previously available benchmarks, thus demonstrating the scalability and effectiveness of our approach.

Published as a conference paper at ICLR 2022

References in corpus (12)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Simplifying Graph Convolutional Networks
• Variational Graph Auto-Encoders
• Deep Graph Contrastive Representation Learning
• Contrastive Multi-View Representation Learning on Graphs
• OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
• Graph Barlow Twins: A self-supervised representation learning framework for graphs
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Understanding self-supervised Learning Dynamics without Contrastive Pairs
• Large-scale graph representation learning with very deep GNNs and self-supervision
• Self-supervised Graph Neural Networks without explicit negative sampling
• Self-supervised Graph Representation Learning via Bootstrapping

Cited by in corpus (1)

• Graph Self-Supervised Learning with Learnable Structural and Positional Encodings