Heterogeneous Graph Benchmarks
ACM
Structure
1Graphs
10,942Nodes
547,872Edges
3Classes
1902Node Feature Dim
Coverage
352Results
1Variants
38Papers
- Towards Efficient LLM-aware Heterogeneous Graph Learning Towards Efficient LLM-aware Heterogeneous Graph Learning
- Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors
- NeurIPS 2024: Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective NeurIPS 2024
- KDD 2024: Revisiting Graph Autoencoders as Implicit Contrastive Learners Revisiting Graph Autoencoders as Implicit Contrastive Learners KDD 2024
- IGNN-Solver: A Graph Neural Solver for Implicit Graph Neural Networks IGNN-Solver: A Graph Neural Solver for Implicit Graph Neural Networks
- NeurIPS 2024: Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning NeurIPS 2024
- NeurIPS 2024: Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers NeurIPS 2024
- SynC: Synergistic Boosting of Structure and Representation for Deep Graph Clustering SynC: Synergistic Boosting of Structure and Representation for Deep Graph Clustering
- ICML 2024: SlotGAT: Slot-based Message Passing for Heterogeneous Graphs SlotGAT: Slot-based Message Passing for Heterogeneous Graphs ICML 2024
- Generative-Contrastive Heterogeneous Graph Neural Network Generative-Contrastive Heterogeneous Graph Neural Network
- ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks
- CDC: A Simple Framework for Complex Data Clustering CDC: A Simple Framework for Complex Data Clustering
- Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph
- ICML 2023: Graph Neural Networks with a Distribution of Parametrized Graphs Graph Neural Networks with a Distribution of Parametrized Graphs ICML 2023
- Efficient Heterogeneous Graph Learning via Random Projection Efficient Heterogeneous Graph Learning via Random Projection
- WWW 2023: HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks WWW 2023
- PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection
- SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning
- Collaborative Graph Neural Networks for Attributed Network Embedding Collaborative Graph Neural Networks for Attributed Network Embedding
- NeurIPS 2023: Long-range Meta-path Search on Large-scale Heterogeneous Graphs Long-range Meta-path Search on Large-scale Heterogeneous Graphs NeurIPS 2023
- WWW 2023: Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials WWW 2023
- GANN: Graph Alignment Neural Network for Semi-Supervised Learning GANN: Graph Alignment Neural Network for Semi-Supervised Learning
- Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networks Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networks
- WWW 2023: Homophily-oriented Heterogeneous Graph Rewiring Homophily-oriented Heterogeneous Graph Rewiring WWW 2023
- Heterogeneous Graph Contrastive Multi-view Learning Heterogeneous Graph Contrastive Multi-view Learning
- Structure-Preserving Graph Representation Learning Structure-Preserving Graph Representation Learning
- AAAI 2022: Simple and Efficient Heterogeneous Graph Neural Network Simple and Efficient Heterogeneous Graph Neural Network AAAI 2022
- Geometry Contrastive Learning on Heterogeneous Graphs Geometry Contrastive Learning on Heterogeneous Graphs
- Mixed Graph Contrastive Network for Semi-Supervised Node Classification Mixed Graph Contrastive Network for Semi-Supervised Node Classification
- Improved Dual Correlation Reduction Network Improved Dual Correlation Reduction Network
- NeurIPS 2021: Multi-view Contrastive Graph Clustering Multi-view Contrastive Graph Clustering NeurIPS 2021
- Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection
- KDD 2021: Heterogeneous Graph Benchmarks Heterogeneous Graph Benchmarks KDD 2021
- AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
- Scalable Graph Neural Networks for Heterogeneous Graphs Scalable Graph Neural Networks for Heterogeneous Graphs
- NeurIPS 2020: Implicit Graph Neural Networks Implicit Graph Neural Networks NeurIPS 2020
- NeurIPS 2020: Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs NeurIPS 2020
- KDD 2020: AM-GCN: Adaptive Multi-channel Graph Convolutional Networks AM-GCN: Adaptive Multi-channel Graph Convolutional Networks KDD 2020
3-class node classification Heterogeneous ACM academic graph — classify paper nodes (3 areas). Uses typed nodes, typed relations, and available type-specific features. Evaluated by Micro-F1.
Dataset details
Task
Heterogeneous ACM academic graph — classify paper nodes (3 areas). The primary catalog metric is Micro-F1.
Data
Heterogeneous ACM academic graph — classify paper nodes (3 areas). The cataloged artifact reports 1 graphs, 3 target classes or tasks.
Features
Inputs are typed graphs with relation-specific edges and type-specific feature matrices where available. Some node types lack native features, so learned embeddings or propagated features are modeling choices rather than measured attributes.
Splits and evaluation
The catalog records these protocols or variants: Standard split. Evaluation uses Micro-F1 (higher is better). Exact masks or folds must come from the cited release.
Quirks and pitfalls
Schema, reverse-edge creation, feature propagation, and negative sampling materially affect results. Report the exact release and target type; random edge splits may leak future or reciprocal information.
Sources
SOTA Progression
new SOTA
matches SOTA at that time
other proposed result
other baseline result
Leaderboard
| # | Model | Micro-F1 ↑ | ACC | ARI | AUC | Accuracy | F1 | F1-micro | Macro-F1 | Mi-F1 (Micro-F1) | NMI | ROC-AUC | Paper |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | LMSPS | 0.9469
±
0.0036 | — | — | — | — | — | — | — | — | — | — | |
| 2 | PSHGCN | 0.9427
±
0.0023 | — | — | — | — | — | — | — | — | — | — | |
| 3 | SlotGAT | 0.9406
±
0.0022 | — | — | — | — | — | — | — | — | — | — | |
| 4 | RpHGNN | 0.9404
±
0.0059 | — | — | — | — | — | — | — | — | — | — | |
| 5 | SeHGNN | 0.9398
±
0.0036 | — | — | — | — | — | — | — | — | — | — | |
| 6 | EMRGNN | 0.9385
±
0.0033 | — | — | — | — | — | — | — | — | — | — | |
| 7 | HINormer | 0.9383
±
0.0045 | — | — | — | — | — | — | — | — | — | — | |
| 8 | PMMM | 0.9371
±
0.0017 | — | — | — | — | — | — | — | — | — | — | |
| 9 | SHGN | 0.9335
±
0.0045 Macro-F1
0.9342
±
0.0044 | — | — | — | — | — | — | 0.9342
±
0.0044 | — | — | — | |
| 10 | HGB | 0.9335
±
0.0045 | — | — | — | — | — | — | — | — | — | — | |
| 11 | InfoMGF-LA | 0.9335
±
0.0021 | — | — | — | — | — | — | — | — | — | — | |
| 12 | Simple-HGN | 0.9335
±
0.0045 | — | — | — | — | — | — | — | — | — | — | |
| 13 | simpleHGN | 0.9335
±
0.0045 | — | — | — | — | — | — | — | — | — | — | |
| 14 | NARS | 0.9331
±
0.0033 | — | — | — | — | — | — | — | — | — | — | |
| 15 | InfoMGF-RA | 0.9314
±
0.0021 | — | — | — | — | — | — | — | — | — | — | |
| 16 | HALO | 0.9296
±
0.0033 | — | — | — | — | — | — | — | — | — | — | |
| 17 | GRCN | 0.9294
±
0.0018 | — | — | — | — | — | — | — | — | — | — | |
| 18 | HDHGR | 0.9280
±
0.0025 Macro-F1
0.9287
±
0.0024 | — | — | — | — | — | — | 0.9287
±
0.0024 | — | — | — | |
| 19 | GAT | 0.9273 | — | — | — | — | — | — | — | — | — | — | |
| 20 | Simple-HGN | 0.9273
±
0.0021 | — | — | — | — | — | — | — | — | — | — | |
| 21 | EM-GCN[PT] | 0.9270
±
0.0026 | — | — | — | — | — | — | — | — | — | — | |
| 22 | SCHOOL | 0.9260
±
0.0050 | — | — | — | — | — | — | — | — | — | — | |
| 23 | GTN | 0.9258 | — | — | — | — | — | — | — | — | — | — | |
| 24 | GraphMSE | 0.9254
±
0.0014 | — | — | — | — | — | — | — | — | — | — | |
| 25 | SeHGNN | 0.9245
±
0.0017 | — | — | — | — | — | — | — | — | — | — | |
| 26 | DisenHAN | 0.9245
±
0.0033 | — | — | — | — | — | — | — | — | — | — | |
| 27 | space4HGNN | 0.9238
±
0.0010 | — | — | — | — | — | — | — | — | — | — | |
| 28 | EM-GCN[PO] | 0.9235
±
0.0038 | — | — | — | — | — | — | — | — | — | — | |
| 29 | ChebNetII | 0.9233
±
0.0038 | — | — | — | — | — | — | — | — | — | — | |
| 30 | EM-GCN[PD] | 0.9231
±
0.0043 | — | — | — | — | — | — | — | — | — | — | |
| 31 | GCN | 0.9229 | — | — | — | — | — | — | — | — | — | — | |
| 32 | GPRGNN | 0.9228
±
0.0027 | — | — | — | — | — | — | — | — | — | — | |
| 33 | SGC | 0.9224 | — | — | — | — | — | — | — | — | — | — | |
| 34 | HINormer | 0.9219
±
0.0040 | — | — | — | — | — | — | — | — | — | — | |
| 35 | EM-GCN[PH] | 0.9218
±
0.0052 | — | — | — | — | — | — | — | — | — | — | |
| 36 | SUBLIME | 0.9213
±
0.0037 | — | — | — | — | — | — | — | — | — | — | |
| 37 | GTN | 0.9212
±
0.0062 | — | — | — | — | — | — | — | — | — | — | |
| 38 | GSR | 0.9211
±
0.0099 | — | — | — | — | — | — | — | — | — | — | |
| 39 | HERO | 0.9210
±
0.0070 | — | — | — | — | — | — | — | — | — | — | |
| 40 | LDS | 0.9205
±
0.0026 | — | — | — | — | — | — | — | — | — | — | |
| 41 | MHGCN | 0.9197
±
0.0068 | — | — | — | — | — | — | — | — | — | — | |
| 42 | HDMI + HetGPT | 0.9194
±
0.0033 | — | — | — | — | — | — | — | — | — | — | |
| 43 | GCN | 0.9192
±
0.0040 | — | — | — | — | — | — | — | — | — | — | |
| 44 | IDGL | 0.9163
±
0.0124 | — | — | — | — | — | — | — | — | — | — | |
| 45 | BTGF | 0.9162
±
0.0011 | — | — | — | — | — | — | — | — | — | — | |
| 46 | MCGC | 0.9155 | — | — | — | — | — | — | — | — | — | — | |
| 47 | HAN | 0.9147
±
0.0022 | — | — | — | — | — | — | — | — | — | — | |
| 48 | GAT | 0.9146
±
0.0062 | — | — | — | — | — | — | — | — | — | — | |
| 49 | RGCN | 0.9141
±
0.0075 | — | — | — | — | — | — | — | — | — | — | |
| 50 | HGCML-P | 0.9134
±
0.0017 | — | — | — | — | — | — | — | — | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time