# GraphCL: Contrastive Self-Supervised Learning of Graph Representations

arXiv: https://arxiv.org/abs/2007.08025 · HTML: https://mlsanity.com/paper/2007.08025/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 26 of 26)

- [Graph Self-Supervised Learning: A Survey](https://mlsanity.com/paper/2103.00111/) (2021)
- [Motif-based Graph Self-Supervised Learning for Molecular Property Prediction](https://mlsanity.com/paper/2110.00987/) (2021)
- [Spectral Feature Augmentation for Graph Contrastive Learning and Beyond](https://mlsanity.com/paper/2212.01026/) (2022)
- [COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning](https://mlsanity.com/paper/2206.04726/) (2022)
- [Graph Communal Contrastive Learning](https://mlsanity.com/paper/2110.14863/) (2021)
- [Double-Scale Self-Supervised Hypergraph Learning for Group Recommendation](https://mlsanity.com/paper/2109.04200/) (2021)
- [TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning](https://mlsanity.com/paper/2112.03587/) (2021)
- [Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs](https://mlsanity.com/paper/2310.09872/) (2023)
- [When to Pre-Train Graph Neural Networks? From Data Generation Perspective!](https://mlsanity.com/paper/2303.16458/) (2023)
- [Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks](https://mlsanity.com/paper/2311.01038/) (2023)
- [Multi-behavior Self-supervised Learning for Recommendation](https://mlsanity.com/paper/2305.18238/) (2023)
- [Motif-based Graph Representation Learning with Application to Chemical Molecules](https://mlsanity.com/paper/2208.04529/) (2022)
- [Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning](https://mlsanity.com/paper/2310.18209/) (2023)
- [Generative Subgraph Contrast for Self-Supervised Graph Representation Learning](https://mlsanity.com/paper/2207.11996/) (2022)
- [Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval](https://mlsanity.com/paper/2101.00820/) (2021)
- [Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples](https://mlsanity.com/paper/2212.13847/) (2022)
- [Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning](https://mlsanity.com/paper/2403.05770/) (2024)
- [How to Use Graph Data in the Wild to Help Graph Anomaly Detection?](https://mlsanity.com/paper/2506.04190/) (2025)
- [Negative as Positive: Enhancing Out-of-distribution Generalization for Graph Contrastive Learning](https://mlsanity.com/paper/2405.16224/) (2024)
- [Invariant Graph Learning Meets Information Bottleneck for Out-of-Distribution Generalization](https://mlsanity.com/paper/2408.01697/) (2024)
- [Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules](https://mlsanity.com/paper/2608.22642/) (2026)
- [Supervised Contrastive Learning as Multi-Objective Optimization for Fine-Tuning Large Pre-trained Language Models](https://mlsanity.com/paper/2209.14161/) (2022)
- [MoleCode unlocks structural intelligence in large language models](https://mlsanity.com/paper/2605.16480/) (2026)
- [Unified GCNs: Towards Connecting GCNs with CNNs](https://mlsanity.com/paper/2204.12300/) (2022)
- [Gaussian Graph with Prototypical Contrastive Learning in E-Commerce Bundle Recommendation](https://mlsanity.com/paper/2307.13468/) (2023)
- [Graph-level Protein Representation Learning by Structure Knowledge Refinement](https://mlsanity.com/paper/2401.02713/) (2024)

## Abstract (arXiv)

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.