mlsanityData to 7 Oct 2026

LAMP: Learnable Meta-Path Guided Adversarial Contrastive Learning for Heterogeneous Graphs

arXiv 2409.06323 ↗First posted 10 Sep 2024cs.LG cs.AI cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

Heterogeneous graph neural networks (HGNNs) have significantly propelled the information retrieval (IR) field. Still, the effectiveness of HGNNs heavily relies on high-quality labels, which are often expensive to acquire. This challenge has shifted attention towards Heterogeneous Graph Contrastive Learning (HGCL), which usually requires pre-defined meta-paths. However, our findings reveal that meta-path combinations significantly affect performance in unsupervised settings, an aspect often overlooked in current literature. Existing HGCL methods have considerable variability in outcomes across different meta-path combinations, thereby challenging the optimization process to achieve consistent and high performance. In response, we introduce textsfLAMP (underlineLearnunderlineAble underlineMeta-underlinePath), a novel adversarial contrastive learning approach that integrates various meta-path sub-graphs into a unified and stable structure, leveraging the overlap among these sub-graphs. To address the denseness of this integrated sub-graph, we propose an adversarial training strategy for edge pruning, maintaining sparsity to enhance model performance and robustness. textsfLAMP aims to maximize the difference between meta-path and network schema views for guiding contrastive learning to capture the most meaningful information. Our extensive experimental study conducted on four diverse datasets from the Heterogeneous Graph Benchmark (HGB) demonstrates that textsfLAMP significantly outperforms existing state-of-the-art unsupervised models in terms of accuracy and robustness.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 10 Sep 2024.

Builds on

39 of 61 references.

References · 39

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  6. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  7. 2018Deep Graph Infomaxcited by 1,101
  8. 2019Heterogeneous Graph Attention Networkcited by 732
  9. 2020Heterogeneous Graph Transformercited by 581
  10. 2019Graph Transformer Networkscited by 520
  11. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  12. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
27 more
  1. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  2. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  3. 2021Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learningcited by 130
  4. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  5. 2019Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscited by 111
  6. 2019Unsupervised Attributed Multiplex Network Embeddingcited by 95
  7. 2021HDMI: High-order Deep Multiplex Infomaxcited by 82
  8. 2019An Attention-based Graph Neural Network for Heterogeneous Structural Learningcited by 71
  9. 2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
  10. 2020RealFormer: Transformer Likes Residual Attentioncited by 62
  11. 2023Heterogeneous Graph Contrastive Learning for Recommendationcited by 28
  12. 2022Multiplex Heterogeneous Graph Convolutional Networkcited by 27
  13. 2021Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendationcited by 22
  14. 2020Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networkscited by 19
  15. 2021X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learningcited by 19
  16. 2023Homophily-oriented Heterogeneous Graph Rewiringcited by 18
  17. 2024Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approachcited by 17
  18. 2021Heterogeneous Contrastive Learningcited by 15
  19. 2021Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspectivecited by 14
  20. 2022Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graphcited by 14
  21. 2023Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptronscited by 12
  22. 2023Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networkscited by 9
  23. 2023DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognitioncited by 6
  24. 2024The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphscited by 6
  25. 2021HeteroQA: Learning towards Question-and-Answering through Multiple Information Sources via Heterogeneous Graph Modelingcited by 4
  26. 2023Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graphcited by 3
  27. 2022Cross-view Self-Supervised Learning on Heterogeneous Graph Neural Network via Bootstrappingcited by 2

Built on by

Not cited yet.