Heterogeneous Graph Benchmarks
DBLP
Structure
1Graphs
26,128Nodes
239,566Edges
4Classes
334Node Feature Dim
Coverage
534Results
1Variants
62Papers
- Adaptive Negative Scheduling for Graph Contrastive Learning Adaptive Negative Scheduling for Graph Contrastive Learning
- ICLR 2026: Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors ICLR 2026
- AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation
- Coden: Efficient Temporal Graph Neural Networks for Continuous Prediction Coden: Efficient Temporal Graph Neural Networks for Continuous Prediction
- Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms
- Towards Efficient LLM-aware Heterogeneous Graph Learning Towards Efficient LLM-aware Heterogeneous Graph Learning
- Non-Dissipative Graph Propagation for Non-Local Community Detection Non-Dissipative Graph Propagation for Non-Local Community Detection
- Dynamic Graph Condensation Dynamic Graph Condensation
- H$ $GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs H$ $GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs
- TMLR 2025: BN-Pool: Bayesian Nonparametric Pooling for Graphs BN-Pool: Bayesian Nonparametric Pooling for Graphs TMLR 2025
- TMLR 2024: Extending Graph Condensation to Multi-Label Datasets: A Benchmark Study Extending Graph Condensation to Multi-Label Datasets: A Benchmark Study TMLR 2024
- NeurIPS 2024: Graph Neural Networks Need Cluster-Normalize-Activate Modules Graph Neural Networks Need Cluster-Normalize-Activate Modules NeurIPS 2024
- 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
- NeurIPS 2024: Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning NeurIPS 2024
- Graph Structure Prompt Learning: A Novel Methodology to Improve Performance of Graph Neural Networks Graph Structure Prompt Learning: A Novel Methodology to Improve Performance of Graph Neural Networks
- SynC: Synergistic Boosting of Structure and Representation for Deep Graph Clustering SynC: Synergistic Boosting of Structure and Representation for Deep Graph Clustering
- From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning
- ICML 2024: Rethinking Independent Cross-Entropy Loss For Graph-Structured Data Rethinking Independent Cross-Entropy Loss For Graph-Structured Data ICML 2024
- 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
- CDC: A Simple Framework for Complex Data Clustering CDC: A Simple Framework for Complex Data Clustering
- ICML 2024: Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective ICML 2024
- Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph
- KDD 2023: Variational Graph Autoencoder for Heterogeneous Information Networks with Missing and Inaccurate Attributes Variational Graph Autoencoder for Heterogeneous Information Networks with Missing and Inaccurate Attributes KDD 2023
- 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
- ULTRA-DP: Unifying Graph Pre-training with Multi-task Graph Dual Prompt ULTRA-DP: Unifying Graph Pre-training with Multi-task Graph Dual Prompt
- WWW 2023: GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning WWW 2023
- ICML 2023: Perfect Alignment May be Poisonous to Graph Contrastive Learning Perfect Alignment May be Poisonous to Graph Contrastive Learning ICML 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
- ICLR 2023: Deep Temporal Graph Clustering Deep Temporal Graph Clustering ICLR 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: 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
- NeurIPS 2022: Graph Few-shot Learning with Task-specific Structures Graph Few-shot Learning with Task-specific Structures NeurIPS 2022
- Heterogeneous Graph Contrastive Multi-view Learning Heterogeneous Graph Contrastive Multi-view Learning
- Relational Self-Supervised Learning on Graphs Relational Self-Supervised Learning on Graphs
- Enhancing Graph Contrastive Learning with Node Similarity Enhancing Graph Contrastive Learning with Node Similarity
- 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
- AAAI 2022: I'm Me, We're Us, and I'm Us: Tri-directional Contrastive Learning on Hypergraphs I'm Me, We're Us, and I'm Us: Tri-directional Contrastive Learning on Hypergraphs AAAI 2022
- Mixed Graph Contrastive Network for Semi-Supervised Node Classification Mixed Graph Contrastive Network for Semi-Supervised Node Classification
- TMLR 2022: Unsupervised Network Embedding Beyond Homophily Unsupervised Network Embedding Beyond Homophily TMLR 2022
- Improved Dual Correlation Reduction Network Improved Dual Correlation Reduction Network
- Graph Representation Learning via Aggregation Enhancement Graph Representation Learning via Aggregation Enhancement
- Model Stealing Attacks Against Inductive Graph Neural Networks Model Stealing Attacks Against Inductive Graph Neural Networks
- Gophormer: Ego-Graph Transformer for Node Classification Gophormer: Ego-Graph Transformer for Node Classification
- NeurIPS 2021: Multi-view Contrastive Graph Clustering Multi-view Contrastive Graph Clustering NeurIPS 2021
- KDD 2021: Heterogeneous Graph Benchmarks Heterogeneous Graph Benchmarks KDD 2021
- Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks
- NeurIPS 2020: Implicit Graph Neural Networks Implicit Graph Neural Networks NeurIPS 2020
- Deep Graph Contrastive Representation Learning Deep Graph Contrastive Representation Learning
- Directed Graph Convolutional Network Directed Graph Convolutional Network
- NeurIPS 2020: Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks NeurIPS 2020
- IJCAI 2019: Node Embedding over Temporal Graphs Node Embedding over Temporal Graphs IJCAI 2019
- Attributed Network Embedding for Learning in a Dynamic Environment Attributed Network Embedding for Learning in a Dynamic Environment
- Dynamic Graph Convolutional Networks Dynamic Graph Convolutional Networks
4-class node classification Heterogeneous academic graph — classify author nodes (4 research areas). Uses typed nodes, typed relations, and available type-specific features. Evaluated by Micro-F1.
Dataset details
Task
Heterogeneous academic graph — classify author nodes (4 research areas). The primary catalog metric is Micro-F1.
Data
Heterogeneous academic graph — classify author nodes (4 research areas). The cataloged artifact reports 1 graphs, 4 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 | Accuracy | COS | Conductance | F1 | F1-micro | Macro F1 | Macro-F1 | NMI | ROC-AUC | Unweighted F1 Measure | Paper |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | LMSPS | 0.9566
±
0.0020 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 2 | PSHGCN | 0.9561
±
0.0012 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 3 | RpHGNN | 0.9555
±
0.0029 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 4 | FusedGAT+GPL | 0.9544
±
0.0023 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 5 | SeHGNN | 0.9542
±
0.0017 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 6 | SlotGAT | 0.9531
±
0.0019 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 7 | MHGCN | 0.9520
±
0.0203 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 8 | PMMM | 0.9514
±
0.0022 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 9 | EM-GCN[PT] | 0.9506
±
0.0039 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 10 | GraMI | 0.9503 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 11 | EM-GCN[PH] | 0.9502
±
0.0019 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 12 | EM-GCN[PO] | 0.9495
±
0.0024 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 13 | HINormer | 0.9494
±
0.0021 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 14 | EM-GCN[PD] | 0.9489
±
0.0017 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 15 | SeHGNN | 0.9486
±
0.0014 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 16 | SHGN (HDHGR) | 0.9473
±
0.0016 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 17 | SCHOOL | 0.9470
±
0.0040 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 18 | ConCH | 0.9470 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 19 | GAT (HDHGR) | 0.9470
±
0.0011 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 20 | space4HGNN | 0.9463
±
0.0040 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 21 | NARS | 0.9461
±
0.0042 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 22 | GCN | 0.9460
±
0.0031 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 23 | MAGNN | 0.9456 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 24 | GAT | 0.9448
±
0.0022 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 25 | simpleHGN | 0.9446
±
0.0020 Macro-F1
0.9401
±
0.0027 | — | — | — | — | — | — | — | — | 0.9401
±
0.0027 | — | — | — | |
| 26 | HGB | 0.9446
±
0.0022 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 27 | Simple-HGN | 0.9446
±
0.0022 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 28 | GraphMSE | 0.9444
±
0.0013 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 29 | HERO | 0.9440
±
0.0040 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 30 | HGCA | 0.9434 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 31 | DiffMG | 0.9420
±
0.0036 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 32 | DisenHAN | 0.9418
±
0.0036 Macro-F1
0.9366
±
0.0039 | — | — | — | — | — | — | — | — | 0.9366
±
0.0039 | — | — | — | |
| 33 | Transformer | 0.9399
±
0.0011 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 34 | GTN | 0.9397
±
0.0054 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 35 | Random | 0.9384
±
0.0053 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 36 | RSHN | 0.9381
±
0.0055 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 37 | CPIM | 0.9380
±
0.0080 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 38 | MAGNN | 0.9376
±
0.0045 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 39 | LINKX (HDHGR) | 0.9369
±
0.0026 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 40 | HAN | 0.9369 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 41 | HGT | 0.9365 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 42 | HGCML-P | 0.9344
±
0.0008 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 43 | HGMAE | 0.9340
±
0.0060 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 44 | FusedGAT | 0.9340
±
0.0020 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 45 | GAT | 0.9339
±
0.0030 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 46 | HetGNN | 0.9336 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 47 | DMGI | 0.9331 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 48 | HGCML | 0.9329
±
0.0012 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 49 | GCN | 0.9310 | — | — | — | — | — | — | — | — | — | — | — | — | |
| 50 | GraphSAGE | 0.9306
±
0.0047 | — | — | — | — | — | — | — | — | — | — | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time