Heterogeneous Graph Benchmarks
IMDB
Structure
1Graphs
21,420Nodes
86,642Edges
5Classes
3066Node Feature Dim
Coverage
226Results
1Variants
25Papers
- Towards Efficient LLM-aware Heterogeneous Graph Learning Towards Efficient LLM-aware Heterogeneous Graph Learning
- KDD 2024: Revisiting Graph Autoencoders as Implicit Contrastive Learners Revisiting Graph Autoencoders as Implicit Contrastive Learners KDD 2024
- Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
- Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models
- ICML 2024: SlotGAT: Slot-based Message Passing for Heterogeneous Graphs SlotGAT: Slot-based Message Passing for Heterogeneous Graphs ICML 2024
- 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
- 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
- Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networks Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networks
- WWW 2023: HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer WWW 2023
- 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
- Relational Self-Supervised Learning on Graphs Relational Self-Supervised Learning on Graphs
- KDD 2022: Multiplex Heterogeneous Graph Convolutional Network Multiplex Heterogeneous Graph Convolutional Network KDD 2022
- 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
- WWW 2022: Exploring Edge Disentanglement for Node Classification Exploring Edge Disentanglement for Node Classification WWW 2022
- NeurIPS 2021: Multi-view Contrastive Graph Clustering Multi-view Contrastive Graph Clustering NeurIPS 2021
- KDD 2021: Heterogeneous Graph Benchmarks Heterogeneous Graph Benchmarks KDD 2021
- Heterogeneous Graph Representation Learning with Relation Awareness Heterogeneous Graph Representation Learning with Relation Awareness
- 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
5-label node classification Heterogeneous IMDB graph — classify movie nodes (5 genres). Uses typed nodes, typed relations, and available type-specific features. Evaluated by Micro-F1.
Dataset details
Task
Heterogeneous IMDB graph — classify movie nodes (5 genres). The primary catalog metric is Micro-F1.
Data
Heterogeneous IMDB graph — classify movie nodes (5 genres). The cataloged artifact reports 1 graphs, 5 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 | Accuracy | F1 | F1-macro | Macro F1 | Mi-F1 (Micro-F1) | Paper |
|---|---|---|---|---|---|---|---|---|---|
| 1 | ELLA | 0.7930
±
0.0010 | — | — | — | — | — | — | |
| 2 | MHGCN | 0.7820
±
0.0138 | — | — | — | — | — | — | |
| 3 | PSHGCN | 0.7446
±
0.0032 | — | — | — | — | — | — | |
| 4 | HALO | 0.7381
±
0.0072 | — | — | — | — | — | — | |
| 5 | SeHGNN | 0.7342
±
0.0047 | — | — | — | — | — | — | |
| 6 | simpleHGN | 0.7083
±
0.0107 | — | — | — | — | — | — | |
| 7 | MHGCN | 0.7028
±
0.0071 | — | — | — | — | — | — | |
| 8 | RpHGNN | 0.6977
±
0.0066 | — | — | — | — | — | — | |
| 9 | SeHGNN | 0.6917
±
0.0043 | — | — | — | — | — | — | |
| 10 | GPRGNN | 0.6883
±
0.0095 | — | — | — | — | — | — | |
| 11 | EMRGNN | 0.6876
±
0.0078 | — | — | — | — | — | — | |
| 12 | LMSPS | 0.6870
±
0.0026 | — | — | — | — | — | — | |
| 13 | SlotGAT | 0.6864
±
0.0033 | — | — | — | — | — | — | |
| 14 | ChebNetII | 0.6833
±
0.0092 | — | — | — | — | — | — | |
| 15 | GTN | 0.6827
±
0.0065 | — | — | — | — | — | — | |
| 16 | SeHGNN | 0.6821
±
0.0032 | — | — | — | — | — | — | |
| 17 | GCN | 0.6813
±
0.0083 | — | — | — | — | — | — | |
| 18 | GAT | 0.6808
±
0.0049 | — | — | — | — | — | — | |
| 19 | HINormer | 0.6783
±
0.0034 | — | — | — | — | — | — | |
| 20 | MAGNN | 0.6782
±
0.0154 | — | — | — | — | — | — | |
| 21 | HAN | 0.6769
±
0.0064 | — | — | — | — | — | — | |
| 22 | PMMM | 0.6758
±
0.0022 | — | — | — | — | — | — | |
| 23 | DisenHAN | 0.6748
±
0.0045 | — | — | — | — | — | — | |
| 24 | HGB | 0.6736
±
0.0057 | — | — | — | — | — | — | |
| 25 | Simple-HGN | 0.6736
±
0.0057 | — | — | — | — | — | — | |
| 26 | simpleHGN | 0.6736
±
0.0057 | — | — | — | — | — | — | |
| 27 | GraphAdapter | 0.6730
±
0.0050 | — | — | — | — | — | — | |
| 28 | HGT | 0.6720
±
0.0057 | — | — | — | — | — | — | |
| 29 | GHGRL | 0.6670
±
0.0110 | — | — | — | — | — | — | |
| 30 | RGCN | 0.6651
±
0.0028 | — | — | — | — | — | — | |
| 31 | Transformer | 0.6629
±
0.0069 | — | — | — | — | — | — | |
| 32 | NARS | 0.6618
±
0.0070 | — | — | — | — | — | — | |
| 33 | HDMI | 0.6580 | — | — | — | — | — | — | |
| 34 | RGRL | 0.6580 | — | — | — | — | — | — | |
| 35 | IGNN | 0.6550 | — | — | — | — | — | — | |
| 36 | GCL | 0.6514
±
0.0047 | — | — | — | — | — | — | |
| 37 | GTN | 0.6514
±
0.0045 | — | — | — | — | — | — | |
| 38 | GAT | 0.6486
±
0.0043 | — | — | — | — | — | — | |
| 39 | GCN | 0.6482
±
0.0064 | — | — | — | — | — | — | |
| 40 | DMGI | 0.6480 | — | — | — | — | — | — | |
| 41 | EM-GCN[PT] | 0.6478
±
0.0124 | — | — | — | — | — | — | |
| 42 | MAGNN | 0.6467
±
0.0167 | — | — | — | — | — | — | |
| 43 | HAN | 0.6463
±
0.0058 | — | — | — | — | — | — | |
| 44 | R-HGNN | 0.6417 | — | — | — | — | — | — | |
| 45 | GRACE | 0.6407
±
0.0080 | — | — | — | — | — | — | |
| 46 | AM-GCN | 0.6400
±
0.0013 | — | — | — | — | — | — | |
| 47 | space4HGNN | 0.6396
±
0.0043 | — | — | — | — | — | — | |
| 48 | HGSL | 0.6380
±
0.0030 | — | — | — | — | — | — | |
| 49 | HGT | 0.6365 | — | — | — | — | — | — | |
| 50 | RGCN | 0.6359 | — | — | — | — | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time