mlsanityData to 14 Oct 2026

Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks

arXiv 2112.14936 ↗First posted 30 Dec 2021cs.LG cs.SIcited by 176

Not on the map. Why?

Abstract (arXiv)

Heterogeneous graph neural networks (HGNNs) have been blossoming in recent years, but the unique data processing and evaluation setups used by each work obstruct a full understanding of their advancements. In this work, we present a systematical reproduction of 12 recent HGNNs by using their official codes, datasets, settings, and hyperparameters, revealing surprising findings about the progress of HGNNs. We find that the simple homogeneous GNNs, e.g., GCN and GAT, are largely underestimated due to improper settings. GAT with proper inputs can generally match or outperform all existing HGNNs across various scenarios. To facilitate robust and reproducible HGNN research, we construct the Heterogeneous Graph Benchmark (HGB), consisting of 11 diverse datasets with three tasks. HGB standardizes the process of heterogeneous graph data splits, feature processing, and performance evaluation. Finally, we introduce a simple but very strong baseline Simple-HGN--which significantly outperforms all previous models on HGB--to accelerate the advancement of HGNNs in the future.

Key facts. Cited by 176 papers in the map (data through 14 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 30 Dec 2021.

Builds on

32 of 48 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Graph Attention Networkscited by 8,923
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  9. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  10. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  11. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  12. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
20 more
  1. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  2. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
  3. 2019Heterogeneous Graph Attention Networkcited by 734
  4. 2019Graph Neural Networks for Social Recommendationcited by 714
  5. 2020Heterogeneous Graph Transformercited by 582
  6. 2019Graph Transformer Networkscited by 523
  7. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
  8. 2019KGAT: Knowledge Graph Attention Network for Recommendationcited by 343
  9. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  10. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 303
  11. 2020DeeperGCN: All You Need to Train Deeper GCNscited by 250
  12. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  13. 2019Knowledge Graph Convolutional Networks for Recommender Systemscited by 121
  14. 2019Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systemscited by 107
  15. 2017L2-constrained Softmax Loss for Discriminative Face Verificationcited by 96
  16. 2019Representation Learning for Attributed Multiplex Heterogeneous Networkcited by 91
  17. 2019An Attention-based Graph Neural Network for Heterogeneous Structural Learningcited by 71
  18. 2020Understanding Negative Sampling in Graph Representation Learningcited by 66
  19. 2020RealFormer: Transformer Likes Residual Attentioncited by 62
  20. 2018Semi-supervised Learning on Graphs with Generative Adversarial Netscited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 26; 2023: 40; 2024: 46; 2025: 39; 2026: 25.

176 papers.

Sort:

By area:

  1. 2022Towards Better Evaluation for Dynamic Link Predictioncited by 122
  2. 2025LocAgent: Graph-Guided LLM Agents for Code Localizationcited by 86
  3. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 78
  4. 2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
  5. 2023HGPROMPT: Bridging Homogeneous and Heterogeneous Graphs for Few-shot Prompt Learningcited by 45
  6. 2024HiGPT: Heterogeneous Graph Language Modelcited by 45
  7. 2022TwiBot-22: Towards Graph-Based Twitter Bot Detectioncited by 44
  8. 2022Relational Attention: Generalizing Transformers for Graph-Structured Taskscited by 41
  9. 2024Knowledge Graph Enhanced Large Language Model Editingcited by 40
  10. 2023HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformercited by 35
  11. 2023HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networkscited by 33
  12. 2025Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellencecited by 26
38 more
  1. 2022Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networkscited by 24
  2. 2022Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNscited by 23
  3. 2023Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networkscited by 23
  4. 2024Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Miningcited by 20
  5. 2023Homophily-oriented Heterogeneous Graph Rewiringcited by 18
  6. 2023LMBot: Distilling Graph Knowledge into Language Model for Graph-less Deployment in Twitter Bot Detectioncited by 17
  7. 2023MGTAB: A Multi-Relational Graph-Based Twitter Account Detection Benchmarkcited by 16
  8. 2023Efficient Heterogeneous Graph Learning via Random Projectioncited by 16
  9. 2024OpenFGL: A Comprehensive Benchmark for Federated Graph Learningcited by 16
  10. 2022BRIGHT -- Graph Neural Networks in Real-Time Fraud Detectioncited by 15
  11. 2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
  12. 2023Pretraining Language Models with Text-Attributed Heterogeneous Graphscited by 15
  13. 2024Diet-ODIN: A Novel Framework for Opioid Misuse Detection with Interpretable Dietary Patternscited by 14
  14. 2022ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspectivecited by 12
  15. 2024GC-Bench: An Open and Unified Benchmark for Graph Condensationcited by 12
  16. 2022Neural Graph Databasescited by 11
  17. 20244DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBscited by 11
  18. 2024SlotGAT: Slot-based Message Passing for Heterogeneous Graph Neural Networkcited by 11
  19. 2022DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacycited by 10
  20. 2023Meta-Path Learning for Multi-relational Graph Neural Networkscited by 10
  21. 2024Heterogeneous Sheaf Neural Networkscited by 10
  22. 2022Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networkscited by 9
  23. 2023Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networkscited by 9
  24. 2022Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Networkcited by 8
  25. 2023Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomialscited by 8
  26. 2022Enabling Homogeneous GNNs to Handle Heterogeneous Graphs via Relation Embeddingcited by 7
  27. 2023AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Networkcited by 7
  28. 2024Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Predictioncited by 7
  29. 2024A Self-Explainable Heterogeneous GNN for Relational Deep Learningcited by 7
  30. 2024Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspectivecited by 7
  31. 2022Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learningcited by 6
  32. 2023State of the Art and Potentialities of Graph-level Learningcited by 6
  33. 2024Few-Shot Causal Representation Learning for Out-of-Distribution Generalization on Heterogeneous Graphscited by 6
  34. 2024HGAttack: Transferable Heterogeneous Graph Adversarial Attackcited by 6
  35. 2024When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmarkcited by 6
  36. 2024GuARD: Effective Anomaly Detection through a Text-Rich and Graph-Informed Language Modelcited by 6
  37. 2022Modelling graph dynamics in fraud detection with "Attention"cited by 5
  38. 2023Link Prediction on Latent Heterogeneous Graphscited by 5

50 most cited of 176 All 176 (JSON)