mlsanityData to 14 Oct 2026

Simple and Asymmetric Graph Contrastive Learning without Augmentations

arXiv 2310.18884 ↗First posted 29 Oct 2023cs.LG stat.MLcited by 38

Not on the map. Why?

Abstract (arXiv)

Graph Contrastive Learning (GCL) has shown superior performance in representation learning in graph-structured data. Despite their success, most existing GCL methods rely on prefabricated graph augmentation and homophily assumptions. Thus, they fail to generalize well to heterophilic graphs where connected nodes may have different class labels and dissimilar features. In this paper, we study the problem of conducting contrastive learning on homophilic and heterophilic graphs. We find that we can achieve promising performance simply by considering an asymmetric view of the neighboring nodes. The resulting simple algorithm, Asymmetric Contrastive Learning for Graphs (GraphACL), is easy to implement and does not rely on graph augmentations and homophily assumptions. We provide theoretical and empirical evidence that GraphACL can capture one-hop local neighborhood information and two-hop monophily similarity, which are both important for modeling heterophilic graphs. Experimental results show that the simple GraphACL significantly outperforms state-of-the-art graph contrastive learning and self-supervised learning methods on homophilic and heterophilic graphs. The code of GraphACL is available at https://github.com/tengxiao1/GraphACL.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 52 of its 63 references that are in the map. First posted on arXiv 29 Oct 2023.

Builds on

52 of 63 references.

References · 52

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  8. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  9. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  10. 2016Variational Graph Auto-Encoderscited by 1,382
  11. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  12. 2018Deep Graph Infomaxcited by 1,106
38 more
  1. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  2. 2015Image-based Recommendations on Styles and Substitutescited by 706
  3. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  4. 2015LINE: Large-scale Information Network Embeddingcited by 582
  5. 2019Multi-scale Attributed Node Embeddingcited by 548
  6. 2020Deep Graph Contrastive Representation Learningcited by 539
  7. 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
  8. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  9. 2017Representation Learning on Graphs: Methods and Applicationscited by 457
  10. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 362
  11. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  12. 2021Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Losscited by 313
  13. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 311
  14. 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 242
  15. 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 198
  16. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 186
  17. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  18. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  19. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  20. 2022Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methodscited by 149
  21. 2021From Canonical Correlation Analysis to Self-supervised Graph Neural Networkscited by 141
  22. 2020Domain Adaptation with Conditional Distribution Matching and Generalized Label Shiftcited by 125
  23. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  24. 2020A Unified View on Graph Neural Networks as Graph Signal Denoisingcited by 110
  25. 2022Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlapcited by 105
  26. 2020A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescited by 100
  27. 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
  28. 2022How Mask Matters: Towards Theoretical Understandings of Masked Autoencoderscited by 86
  29. 2021ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learningcited by 72
  30. 2022Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrumcited by 43
  31. 2022Graph Auto-Encoder Via Neighborhood Wasserstein Reconstructioncited by 28
  32. 2022Contrastive Laplacian Eigenmapscited by 24
  33. 2023Learning How to Propagate Messages in Graph Neural Networkscited by 23
  34. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  35. 2023A General Offline Reinforcement Learning Framework for Interactive Recommendationcited by 18
  36. 2022Link Prediction with Non-Contrastive Learningcited by 11
  37. 2022Decoupled Self-supervised Learning for Non-Homophilous Graphscited by 10
  38. 2022Localized Contrastive Learning on Graphscited by 10

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 12; 2025: 17; 2026: 8.

38 papers.

Sort:

By area:

  1. 2024Non-Homophilic Graph Pre-Training and Prompt Learningcited by 31
  2. 2024The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challengescited by 29
  3. 2024How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspectivecited by 14
  4. 2025GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuningcited by 13
  5. 20243M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generationcited by 8
  6. 2024Training MLPs on Graphs without Supervisioncited by 8
  7. 2025Rethinking Graph Contrastive Learning through Relative Similarity Preservationcited by 5
  8. 2026Structure-Centric Graph Foundation Model via Geometric Basescited by 5
  9. 2025Discrepancy-Aware Graph Mask Auto-Encodercited by 4
  10. 2025Str-GCL: Structural Commonsense Driven Graph Contrastive Learningcited by 3
  11. 2026Learning Graph Foundation Models on Riemannian Graph-of-Graphscited by 3
  12. 2024Preventing Collapse in Contrastive Learning with Orthonormal Prototypes (CLOP)cited by 2
26 more
  1. 2024Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learningcited by 2
  2. 2024GeomCLIP: Contrastive Geometry-Text Pre-training for Moleculescited by 2
  3. 2024MIN: Multi-channel Interaction Network for Drug-Target Interaction with Protein Distillationcited by 2
  4. 2025Enhancing Homophily-Heterophily Separation: Relation-Aware Learning in Heterogeneous Graphscited by 2
  5. 2023CueGCL: Cluster-aware Personalized Self-Training for Unsupervised Graph Contrastive Learningcited by 1
  6. 2024Disentangled Generative Graph Representation Learningcited by 1
  7. 2024Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learningcited by 1
  8. 2025HGCL: Hierarchical Graph Contrastive Learning for User-Item Recommendationcited by 1
  9. 2026Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignmentcited by 1
  10. 2026SCGFM-ART: Amortized Relational Transport for Structure-Centric Graph Foundation Modelscited by 1
  11. 2024SimMLP: Training MLPs on Graphs without Supervisioncited by 0
  12. 2025FairACE: Achieving Degree Fairness in Graph Neural Networks via Contrastive and Adversarial Group-Balanced Trainingcited by 0
  13. 2025H3GNNs: Harmonizing Heterophily and Homophily in GNNs via Joint Structural Node Encoding and Self-Supervised Learningcited by 0
  14. 2025Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networkscited by 0
  15. 2025Aligning the Spectrum: Hybrid Graph Pre-training and Prompt Tuning across Homophily and Heterophilycited by 0
  16. 2025Enhancing Contrastive Link Prediction With Edge Balancing Augmentationcited by 0
  17. 2025Enhanced Pre-training of Graph Neural Networks for Million-Scale Heterogeneous Graphscited by 0
  18. 2025Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specializationcited by 0
  19. 2025Adaptive Multi-view Graph Contrastive Learning via Fractional-order Neural Diffusion Networkscited by 0
  20. 2025Optimizing Classification of Infrequent Labels by Reducing Variability in Label Distributioncited by 0
  21. 2025Understanding InfoNCE: Transition Probability Matrix Induced Feature Clusteringcited by 0
  22. 2025Semi-Supervised Contrastive Learning with Orthonormal Prototypescited by 0
  23. 2026RaDAR: Relation-aware Diffusion-Asymmetric Graph Contrastive Learning for Recommendationcited by 0
  24. 2026Neighbourhood Transformer: Switchable Attention for Monophily-Aware Graph Learningcited by 0
  25. 2026Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passingcited by 0
  26. 2026Differentiable Koopman Operator for Contrastive Learning on Dynamic Graphscited by 0