mlsanityData to 7 Oct 2026

Heterogeneous Graph Transformer

arXiv 2003.01332 ↗First posted 3 Mar 2020cs.LG cs.SI stat.MLcited by 581

Not on the map. Why?

Abstract (arXiv)

Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all nodes and edges belong to the same types, making them infeasible to represent heterogeneous structures. In this paper, we present the Heterogeneous Graph Transformer (HGT) architecture for modeling Web-scale heterogeneous graphs. To model heterogeneity, we design node- and edge-type dependent parameters to characterize the heterogeneous attention over each edge, empowering HGT to maintain dedicated representations for different types of nodes and edges. To handle dynamic heterogeneous graphs, we introduce the relative temporal encoding technique into HGT, which is able to capture the dynamic structural dependency with arbitrary durations. To handle Web-scale graph data, we design the heterogeneous mini-batch graph sampling algorithm---HGSampling---for efficient and scalable training. Extensive experiments on the Open Academic Graph of 179 million nodes and 2 billion edges show that the proposed HGT model consistently outperforms all the state-of-the-art GNN baselines by 9%--21% on various downstream tasks.

Key facts. Cited by 581 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 61; 2022: 115; 2023: 124; 2024: 89; 2025: 95; 2026: 97.

581 papers.

Sort:

By area:

  1. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  2. 2021Do Transformers Really Perform Bad for Graph Representation?cited by 318
  3. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 223
  4. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  5. 2024GraphRouter: A Graph-based Router for LLM Selectionscited by 154
  6. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
  7. 2021Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learningcited by 130
  8. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  9. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  10. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  11. 2021Global Self-Attention as a Replacement for Graph Convolutioncited by 113
  12. 2021Graph-Guided Network for Irregularly Sampled Multivariate Time Seriescited by 110
38 more
  1. 2022HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encodingcited by 109
  2. 2022Brain Network Transformercited by 92
  3. 2022Graph Attention Multi-Layer Perceptroncited by 82
  4. 2023Attending to Graph Transformerscited by 81
  5. 2021Graph Representation Learning in Biomedicinecited by 79
  6. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 75
  7. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  8. 2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
  9. 2022A Survey on Graph Representation Learning Methodscited by 66
  10. 2021Anomaly Detection in Dynamic Graphs via Transformercited by 57
  11. 2023GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detectioncited by 57
  12. 2021Federated Social Recommendation with Graph Neural Networkcited by 56
  13. 2023Relational Deep Learning: Graph Representation Learning on Relational Databasescited by 55
  14. 2021Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNscited by 51
  15. 2024AnyGraph: Graph Foundation Model in the Wildcited by 51
  16. 2025PyG 2.0: Scalable Learning on Real World Graphscited by 49
  17. 2022SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learningcited by 47
  18. 2022Heterogeneous Graph Masked Autoencoderscited by 47
  19. 2023Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learningcited by 47
  20. 2023Virtual Node Tuning for Few-shot Node Classificationcited by 46
  21. 2023Exploring Large Language Model for Graph Data Understanding in Online Job Recommendationscited by 45
  22. 2025RelGNN: Composite Message Passing for Relational Deep Learningcited by 45
  23. 2022TwiBot-22: Towards Graph-Based Twitter Bot Detectioncited by 44
  24. 2024HiGPT: Heterogeneous Graph Language Modelcited by 44
  25. 2022Relational Attention: Generalizing Transformers for Graph-Structured Taskscited by 41
  26. 2021Sampling methods for efficient training of graph convolutional networks: A surveycited by 40
  27. 2023MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphscited by 40
  28. 2021Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendationcited by 39
  29. 2022Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queriescited by 39
  30. 2023Generalized Graph Prompt: Toward a Unification of Pre-Training and Downstream Tasks on Graphscited by 39
  31. 2021Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networkscited by 38
  32. 2021A Review of Biomedical Datasets Relating to Drug Discovery: A Knowledge Graph Perspectivecited by 37
  33. 2022Contrastive Meta Learning with Behavior Multiplicity for Recommendationcited by 37
  34. 2022Rewiring with Positional Encodings for Graph Neural Networkscited by 35
  35. 2023HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformercited by 35
  36. 2023Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applicationscited by 33
  37. 2024Graph Machine Learning in the Era of Large Language Models (LLMs)cited by 33
  38. 2022Spatial-Temporal Sequential Hypergraph Network for Crime Prediction with Dynamic Multiplex Relation Learningcited by 32

50 most cited of 581 All 581 (JSON)