mlsanityData to 14 Oct 2026

Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples

arXiv 2212.13847 ↗First posted 28 Dec 2022cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Heterogeneous graph contrastive learning has received wide attention recently. Some existing methods use meta-paths, which are sequences of object types that capture semantic relationships between objects, to construct contrastive views. However, most of them ignore the rich meta-path context information that describes how two objects are connected by meta-paths. Further, they fail to distinguish negative samples, which could adversely affect the model performance. To address the problems, we propose MEOW, which considers both meta-path contexts and weighted negative samples. Specifically, MEOW constructs a coarse view and a fine-grained view for contrast. The former reflects which objects are connected by meta-paths, while the latter uses meta-path contexts and characterizes details on how the objects are connected. Then, we theoretically analyze the InfoNCE loss and recognize its limitations for computing gradients of negative samples. To better distinguish negative samples, we learn hard-valued weights for them based on node clustering and use prototypical contrastive learning to pull close embeddings of nodes in the same cluster. In addition, we propose a variant model AdaMEOW that adaptively learns soft-valued weights of negative samples to further improve node representation. Finally, we conduct extensive experiments to show the superiority of MEOW and AdaMEOW against other state-of-the-art methods.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 28 Dec 2022.

Builds on

34 of 49 references.

References · 34

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2016Variational Graph Auto-Encoderscited by 1,382
  6. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  7. 2018Deep Graph Infomaxcited by 1,106
  8. 2019Heterogeneous Graph Attention Networkcited by 734
  9. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  10. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  11. 2020Contrastive Learning with Hard Negative Samplescited by 628
  12. 2015LINE: Large-scale Information Network Embeddingcited by 582
22 more
  1. 2020Heterogeneous Graph Transformercited by 582
  2. 2020Deep Graph Contrastive Representation Learningcited by 539
  3. 2019Graph Transformer Networkscited by 523
  4. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  5. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 463
  6. 2020Hard Negative Mixing for Contrastive Learningcited by 402
  7. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  8. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  9. 2017Heterogeneous Information Network Embedding for Recommendationcited by 133
  10. 2021Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learningcited by 130
  11. 2019Unsupervised Attributed Multiplex Network Embeddingcited by 95
  12. 2020Contrastive Self-supervised Learning for Graph Classificationcited by 68
  13. 2018NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embeddingcited by 42
  14. 2019Heterogeneous Deep Graph Infomaxcited by 42
  15. 2020Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphscited by 38
  16. 2020GraphCL: Contrastive Self-Supervised Learning of Graph Representationscited by 26
  17. 2020Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networkscited by 19
  18. 2021Towards Robust Graph Contrastive Learningcited by 16
  19. 2021Detecting Communities from Heterogeneous Graphs: A Context Path-based Graph Neural Network Modelcited by 15
  20. 2021Relation-aware Graph Attention Model With Adaptive Self-adversarial Trainingcited by 12
  21. 2021Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learningcited by 3
  22. 2022Cross-view Self-Supervised Learning on Heterogeneous Graph Neural Network via Bootstrappingcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 6.

6 papers.

  1. 2025Enhancing Homophily-Heterophily Separation: Relation-Aware Learning in Heterogeneous Graphscited by 2
  2. 2025Towards Efficient LLM-aware Heterogeneous Graph Learningcited by 2
  3. 2025Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrievalcited by 1
  4. 2025Incorporating Attributes and Multi-Scale Structures for Heterogeneous Graph Contrastive Learningcited by 0
  5. 2025Learning Robust Heterogeneous Graph Representations via Contrastive-Reconstruction under Sparse Semanticscited by 0
  6. 2025Exploring Topological Bias in Heterogeneous Graph Neural Networkscited by 0