mlsanityData to 14 Oct 2026

When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning

arXiv 2409.00687 ↗First posted 1 Sep 2024cs.LG cs.AI cs.SIcited by 12

Not on the map. Why?

Abstract (arXiv)

Unsupervised heterogeneous graph representation learning (UHGRL) has gained increasing attention due to its significance in handling practical graphs without labels. However, heterophily has been largely ignored, despite its ubiquitous presence in real-world heterogeneous graphs. In this paper, we define semantic heterophily and propose an innovative framework called Latent Graphs Guided Unsupervised Representation Learning (LatGRL) to handle this problem. First, we develop a similarity mining method that couples global structures and attributes, enabling the construction of fine-grained homophilic and heterophilic latent graphs to guide the representation learning. Moreover, we propose an adaptive dual-frequency semantic fusion mechanism to address the problem of node-level semantic heterophily. To cope with the massive scale of real-world data, we further design a scalable implementation. Extensive experiments on benchmark datasets validate the effectiveness and efficiency of our proposed framework. The source code and datasets have been made available at https://github.com/zxlearningdeep/LatGRL.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 37 of its 68 references that are in the map. First posted on arXiv 1 Sep 2024.

Builds on

37 of 68 references.

References · 37

  1. 2017Graph Attention Networkscited by 8,923
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  4. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  5. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  6. 2018Deep Graph Infomaxcited by 1,106
  7. 2020What Makes for Good Views for Contrastive Learning?cited by 846
  8. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  9. 2019Heterogeneous Graph Attention Networkcited by 734
  10. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  11. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 448
  12. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
25 more
  1. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 429
  2. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 362
  3. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  4. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  5. 2021Graph Self-Supervised Learning: A Surveycited by 289
  6. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  7. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  8. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  9. 2021Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learningcited by 130
  10. 2019Unsupervised Attributed Multiplex Network Embeddingcited by 95
  11. 2021Cross-domain Contrastive Learning for Unsupervised Domain Adaptationcited by 76
  12. 2021Multi-view Contrastive Graph Clusteringcited by 76
  13. 2023Factorized Contrastive Learning: Going Beyond Multi-view Redundancycited by 75
  14. 2022Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminatingcited by 57
  15. 2022Heterogeneous Graph Masked Autoencoderscited by 47
  16. 2023Beyond Homophily: Reconstructing Structure for Graph-agnostic Clusteringcited by 29
  17. 2022Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Neural Networkscited by 19
  18. 2023Homophily-oriented Heterogeneous Graph Rewiringcited by 18
  19. 2022Heterogeneous Graph Contrastive Multi-view Learningcited by 14
  20. 2023MUSE: Multi-View Contrastive Learning for Heterophilic Graphscited by 13
  21. 2023Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clusteringcited by 12
  22. 2024Robust Graph Structure Learning under Heterophilycited by 11
  23. 2024Balanced Multi-Relational Graph Clusteringcited by 10
  24. 2023Hetero2Net: Heterophily-aware Representation Learning on Heterogenerous Graphscited by 4
  25. 2024Simplified PCNet with Robustnesscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 7.

12 papers.

  1. 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignmentcited by 42
  2. 2025Cooperation of Experts: Fusing Heterogeneous Information with Large Margincited by 6
  3. 2026Structure-Centric Graph Foundation Model via Geometric Basescited by 5
  4. 2025Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneitycited by 3
  5. 2025Enhancing Homophily-Heterophily Separation: Relation-Aware Learning in Heterogeneous Graphscited by 2
  6. 2025Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shiftcited by 0
  7. 2026Weighted Graph Clustering via Scale Contraction and Graph Structure Learningcited by 0
  8. 2026Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learningcited by 0
  9. 2026Robust Learning on Heterogeneous Graphs with Heterophily: A Graph Structure Learning Approachcited by 0
  10. 2026HeterSEED: Semantics-Structure Decoupling for Heterogeneous Graph Learning under Heterophilycited by 0
  11. 2026Bridge the Gaps: Heterogeneous Attributed Graph Clustering via Quaternion Representation Learningcited by 0
  12. 2026Preserving Geometric Integrity in Graph Prompting via Measure-Constrained Optimal Transportcited by 0