mlsanityData to 7 Oct 2026

Disentangled Hyperbolic Representation Learning for Heterogeneous Graphs

arXiv 2406.10367 ↗First posted 14 Jun 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Heterogeneous graphs have attracted a lot of research interests recently due to the success for representing complex real-world systems. However, existing methods have two pain points in embedding them into low-dimensional spaces: the mixing of structural and semantic information, and the distributional mismatch between data and embedding spaces. These two challenges require representation methods to consider the global and partial data distributions while unmixing the information. Therefore, in this paper, we propose Dis-H2GCN, a Disentangled Hyperbolic Heterogeneous Graph Convolutional Network. On the one hand, we leverage the mutual information minimization and discrimination maximization constraints to disentangle the semantic features from comprehensively learned representations by independent message propagation for each edge type, away from the pure structural features. On the other hand, the entire model is constructed upon the hyperbolic geometry to narrow the gap between data distributions and representing spaces. We evaluate our proposed Dis-H2GCN on five real-world heterogeneous graph datasets across two downstream tasks: node classification and link prediction. The results demonstrate its superiority over state-of-the-art methods, showcasing the effectiveness of our method in disentangling and representing heterogeneous graph data in hyperbolic spaces.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 41 of its 74 references that are in the map. First posted on arXiv 14 Jun 2024.

Builds on

41 of 74 references.

References · 41

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  5. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  6. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  7. 2019Heterogeneous Graph Attention Networkcited by 732
  8. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  9. 2020Heterogeneous Graph Transformercited by 581
  10. 2019Hyperbolic Graph Convolutional Neural Networkscited by 400
  11. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  12. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 261
29 more
  1. 2019Hyperbolic Graph Neural Networkscited by 244
  2. 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 233
  3. 2020Structural Deep Clustering Networkcited by 145
  4. 2021Hyperbolic Deep Neural Networks: A Surveycited by 138
  5. 2021Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learningcited by 130
  6. 2020AM-GCN: Adaptive Multi-channel Graph Convolutional Networkscited by 121
  7. 2020Disentangled Graph Collaborative Filteringcited by 118
  8. 2019Learning Disentangled Representations for Recommendationcited by 110
  9. 2015A Survey of Heterogeneous Information Network Analysiscited by 109
  10. 2015PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networkscited by 96
  11. 2020Heterogeneous Graph Neural Networks for Malicious Account Detectioncited by 95
  12. 2019Representation Learning for Attributed Multiplex Heterogeneous Networkcited by 91
  13. 2019Hyperbolic Graph Attention Networkcited by 69
  14. 2021Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Spacecited by 67
  15. 2020Heterogeneous Hypergraph Embedding for Graph Classificationcited by 52
  16. 2021Automated Self-Supervised Learning for Graphscited by 50
  17. 2021Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Conescited by 38
  18. 2021Pseudo-Riemannian Graph Convolutional Networkscited by 30
  19. 2021DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendationcited by 28
  20. 2022Multiplex Heterogeneous Graph Convolutional Networkcited by 27
  21. 2022Exploring Edge Disentanglement for Node Classificationcited by 23
  22. 2022DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graphcited by 21
  23. 2020Enhancing Social Recommendation with Adversarial Graph Convolutional Networkscited by 16
  24. 2022kHGCN: Tree-likeness Modeling via Continuous and Discrete Curvature Learningcited by 14
  25. 2021Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networkscited by 13
  26. 2023HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Predictioncited by 13
  27. 2022Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networkscited by 5
  28. 2023H2TNE: Temporal Heterogeneous Information Network Embedding in Hyperbolic Spacescited by 3
  29. 2023Meta-multigraph Search: Rethinking Meta-structure on Heterogeneous Information Networkscited by 1

Built on by

Not cited yet.