GraphCL: Contrastive Self-Supervised Learning of Graph Representations
arXiv:2007.08025
Abstract
We propose Graph Contrastive Learning (GraphCL), a general framework for learning node representations in a self supervised manner. GraphCL learns node embeddings by maximizing the similarity between the representations of two randomly perturbed versions of the intrinsic features and link structure of the same node's local subgraph. We use graph neural networks to produce two representations of the same node and leverage a contrastive learning loss to maximize agreement between them. In both transductive and inductive learning setups, we demonstrate that our approach significantly outperforms the state-of-the-art in unsupervised learning on a number of node classification benchmarks.
Under review for Neurips 2020
References in corpus (16)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Semi-Supervised Classification with Graph Convolutional Networks
- A Simple Framework for Contrastive Learning of Visual Representations
- Inductive Representation Learning on Large Graphs
- Geometric deep learning: going beyond Euclidean data
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Fast Graph Representation Learning with PyTorch Geometric
- Variational Graph Auto-Encoders
- Predicting multicellular function through multi-layer tissue networks
- Contrastive Multiview Coding
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- How Powerful are Graph Neural Networks?
- On Mutual Information Maximization for Representation Learning
- GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
- Formal Limitations on the Measurement of Mutual Information
Cited by in corpus (8)
- Graph Self-Supervised Learning: A Survey
- COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning
- Graph Communal Contrastive Learning
- Motif-based Graph Self-Supervised Learning for Molecular Property Prediction
- Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples
- Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval
- Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning
- Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks