# ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning

arXiv: https://arxiv.org/abs/2110.02027 · HTML: https://mlsanity.com/paper/2110.02027/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 58 references that are in the map.
- First posted on arXiv 5 Oct 2021.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [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)
- [Representation Learning on Graphs: Methods and Applications](https://mlsanity.com/paper/1709.05584/) (2017)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Debiased Contrastive Learning](https://mlsanity.com/paper/2007.00224/) (2020)
- [Graph Contrastive Learning Automated](https://mlsanity.com/paper/2106.07594/) (2021)
- [Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks](https://mlsanity.com/paper/2007.02901/) (2020)
- [Graph Representation Learning via Graphical Mutual Information Maximization](https://mlsanity.com/paper/2002.01169/) (2020)
- [Adversarial Graph Augmentation to Improve Graph Contrastive Learning](https://mlsanity.com/paper/2106.05819/) (2021)

## Built on by (most cited first, 30 of 72)

- [Hard Sample Aware Network for Contrastive Deep Graph Clustering](https://mlsanity.com/paper/2212.08665/) (2022)
- [Cluster-guided Contrastive Graph Clustering Network](https://mlsanity.com/paper/2301.01098/) (2023)
- [Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure](https://mlsanity.com/paper/2211.10738/) (2022)
- [Dink-Net: Neural Clustering on Large Graphs](https://mlsanity.com/paper/2305.18405/) (2023)
- [Simple and Asymmetric Graph Contrastive Learning without Augmentations](https://mlsanity.com/paper/2310.18884/) (2023)
- [A Systematic Survey of Chemical Pre-trained Models](https://mlsanity.com/paper/2210.16484/) (2022)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource](https://mlsanity.com/paper/2211.12875/) (2022)
- [Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization](https://mlsanity.com/paper/2305.11965/) (2023)
- [LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering](https://mlsanity.com/paper/2405.11801/) (2024)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples](https://mlsanity.com/paper/2410.10365/) (2024)
- [HomoGCL: Rethinking Homophily in Graph Contrastive Learning](https://mlsanity.com/paper/2306.09614/) (2023)
- [GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2306.09612/) (2023)
- [Reinforcement Graph Clustering with Unknown Cluster Number](https://mlsanity.com/paper/2308.06827/) (2023)
- [Contrastive Graph Clustering in Curvature Spaces](https://mlsanity.com/paper/2305.03555/) (2023)
- [Does Negative Sampling Matter? A Review with Insights into its Theory and Applications](https://mlsanity.com/paper/2402.17238/) (2024)
- [Heterogeneous Graph Contrastive Multi-view Learning](https://mlsanity.com/paper/2210.00248/) (2022)
- [One Prompt Fits All: Universal Graph Adaptation for Pretrained Models](https://mlsanity.com/paper/2509.22416/) (2025)
- [GraphLearner: Graph Node Clustering with Fully Learnable Augmentation](https://mlsanity.com/paper/2212.03559/) (2022)
- [Localized Contrastive Learning on Graphs](https://mlsanity.com/paper/2212.04604/) (2022)
- [PTGB: Pre-Train Graph Neural Networks for Brain Network Analysis](https://mlsanity.com/paper/2305.14376/) (2023)
- [Hyperbolic Hierarchical Contrastive Hashing](https://mlsanity.com/paper/2212.08904/) (2022)
- [Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive Learning](https://mlsanity.com/paper/2301.13340/) (2023)
- [Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning](https://mlsanity.com/paper/2310.15523/) (2023)
- [A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective](https://mlsanity.com/paper/2403.16137/) (2024)
- [Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning](https://mlsanity.com/paper/2311.02687/) (2023)
- [ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation](https://mlsanity.com/paper/2308.16689/) (2023)
- [Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning](https://mlsanity.com/paper/2408.05087/) (2024)
- [Neighborhood-based Hard Negative Mining for Sequential Recommendation](https://mlsanity.com/paper/2306.10047/) (2023)

## Abstract (arXiv)

Contrastive Learning (CL) has emerged as a dominant technique for unsupervised representation learning which embeds augmented versions of the anchor close to each other (positive samples) and pushes the embeddings of other samples (negatives) apart. As revealed in recent studies, CL can benefit from hard negatives (negatives that are most similar to the anchor). However, we observe limited benefits when we adopt existing hard negative mining techniques of other domains in Graph Contrastive Learning (GCL). We perform both experimental and theoretical analysis on this phenomenon and find it can be attributed to the message passing of Graph Neural Networks (GNNs). Unlike CL in other domains, most hard negatives are potentially false negatives (negatives that share the same class with the anchor) if they are selected merely according to the similarities between anchor and themselves, which will undesirably push away the samples of the same class. To remedy this deficiency, we propose an effective method, dubbed ProGCL, to estimate the probability of a negative being true one, which constitutes a more suitable measure for negatives' hardness together with similarity. Additionally, we devise two schemes (i.e., ProGCL-weight and ProGCL-mix) to boost the performance of GCL. Extensive experiments demonstrate that ProGCL brings notable and consistent improvements over base GCL methods and yields multiple state-of-the-art results on several unsupervised benchmarks or even exceeds the performance of supervised ones. Also, ProGCL is readily pluggable into various negatives-based GCL methods for performance improvement. We release the code at textcolormagentaurlhttps://github.com/junxia97/ProGCL.