# Prototypical Graph Contrastive Learning

arXiv: https://arxiv.org/abs/2106.09645 · HTML: https://mlsanity.com/paper/2106.09645/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 96 references that are in the map.
- First posted on arXiv 17 Jun 2021.

## Builds on (most cited first, 30 of 51)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [TUDataset: A collection of benchmark datasets for learning with graphs](https://mlsanity.com/paper/2007.08663/) (2020)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [A Theoretical Analysis of Contrastive Unsupervised Representation Learning](https://mlsanity.com/paper/1902.09229/) (2019)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Graph Contrastive Learning with Adaptive Augmentation](https://mlsanity.com/paper/2010.14945/) (2020)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [Debiased Contrastive Learning](https://mlsanity.com/paper/2007.00224/) (2020)

## Built on by (most cited first, 30 of 37)

- [Augmentation-Free Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2112.02472/) (2021)
- [Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning](https://mlsanity.com/paper/2202.06200/) (2022)
- [Mugs: A Multi-Granular Self-Supervised Learning Framework](https://mlsanity.com/paper/2203.14415/) (2022)
- [Graph Communal Contrastive Learning](https://mlsanity.com/paper/2110.14863/) (2021)
- [Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations](https://mlsanity.com/paper/2201.01702/) (2022)
- [Disentangled Contrastive Learning for Social Recommendation](https://mlsanity.com/paper/2208.08723/) (2022)
- [Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment](https://mlsanity.com/paper/2302.07491/) (2023)
- [Evaluating Self-Supervised Learning for Molecular Graph Embeddings](https://mlsanity.com/paper/2206.08005/) (2022)
- [Towards Understanding Why Mask-Reconstruction Pretraining Helps in Downstream Tasks](https://mlsanity.com/paper/2206.03826/) (2022)
- [Towards Faithful and Consistent Explanations for Graph Neural Networks](https://mlsanity.com/paper/2205.13733/) (2022)
- [Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation](https://mlsanity.com/paper/2306.10683/) (2023)
- [TopoImb: Toward Topology-level Imbalance in Learning from Graphs](https://mlsanity.com/paper/2212.08689/) (2022)
- [Relational Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2208.10493/) (2022)
- [Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcity](https://mlsanity.com/paper/2208.12422/) (2022)
- [Link Prediction with Non-Contrastive Learning](https://mlsanity.com/paper/2211.14394/) (2022)
- [Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive Learning](https://mlsanity.com/paper/2301.13340/) (2023)
- [Variational Graph Generator for Multi-View Graph Clustering](https://mlsanity.com/paper/2210.07011/) (2022)
- [Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment](https://mlsanity.com/paper/2301.02791/) (2023)
- [Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning](https://mlsanity.com/paper/2312.14222/) (2023)
- [Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey](https://mlsanity.com/paper/2402.07249/) (2024)
- [ProtoCLIP: Prototypical Contrastive Language Image Pretraining](https://mlsanity.com/paper/2206.10996/) (2022)
- [Rethinking Graph Contrastive Learning through Relative Similarity Preservation](https://mlsanity.com/paper/2505.05533/) (2025)
- [Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges](https://mlsanity.com/paper/2511.13261/) (2025)
- [Improving Molecular Pretraining with Complementary Featurizations](https://mlsanity.com/paper/2209.15101/) (2022)
- [Unifying Graph Contrastive Learning via Graph Message Augmentation](https://mlsanity.com/paper/2401.03638/) (2024)
- [Topology-aware Debiased Self-supervised Graph Learning for Recommendation](https://mlsanity.com/paper/2310.15858/) (2023)
- [ExGRG: Explicitly-Generated Relation Graph for Self-Supervised Representation Learning](https://mlsanity.com/paper/2402.06737/) (2024)
- [Topology Reorganized Graph Contrastive Learning with Mitigating Semantic Drift](https://mlsanity.com/paper/2407.16726/) (2024)
- [Graph Self-Supervised Learning with Learnable Structural and Positional Encodings](https://mlsanity.com/paper/2502.16233/) (2025)
- [Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph](https://mlsanity.com/paper/2505.08168/) (2025)

## Abstract (arXiv)

Graph-level representations are critical in various real-world applications, such as predicting the properties of molecules. But in practice, precise graph annotations are generally very expensive and time-consuming. To address this issue, graph contrastive learning constructs instance discrimination task which pulls together positive pairs (augmentation pairs of the same graph) and pushes away negative pairs (augmentation pairs of different graphs) for unsupervised representation learning. However, since for a query, its negatives are uniformly sampled from all graphs, existing methods suffer from the critical sampling bias issue, i.e., the negatives likely having the same semantic structure with the query, leading to performance degradation. To mitigate this sampling bias issue, in this paper, we propose a Prototypical Graph Contrastive Learning (PGCL) approach. Specifically, PGCL models the underlying semantic structure of the graph data via clustering semantically similar graphs into the same group, and simultaneously encourages the clustering consistency for different augmentations of the same graph. Then given a query, it performs negative sampling via drawing the graphs from those clusters that differ from the cluster of query, which ensures the semantic difference between query and its negative samples. Moreover, for a query, PGCL further reweights its negative samples based on the distance between their prototypes (cluster centroids) and the query prototype such that those negatives having moderate prototype distance enjoy relatively large weights. This reweighting strategy is proved to be more effective than uniform sampling. Experimental results on various graph benchmarks testify the advantages of our PGCL over state-of-the-art methods. Code is publicly available at https://github.com/ha-lins/PGCL.