Heterophily Benchmark
Minesweeper
Structure
1Graphs
10,000Nodes
39,402Edges
2Classes
7Node Feature Dim
0.68Homophily
Coverage
265Results
1Variants
31Papers
- Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
- Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
- 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
- Neighbourhood Transformer: Switchable Attention for Monophily-Aware Graph Learning Neighbourhood Transformer: Switchable Attention for Monophily-Aware Graph Learning
- Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow
- Torch Geometric Pool: the Pytorch library for pooling in Graph Neural Networks Torch Geometric Pool: the Pytorch library for pooling in Graph Neural Networks
- NeurIPS 2025: GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks NeurIPS 2025
- NeurIPS 2025: Relieving the Over-Aggregating Effect in Graph Transformers Relieving the Over-Aggregating Effect in Graph Transformers NeurIPS 2025
- Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specialization Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specialization
- Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
- Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax
- TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows
- KDD 2025: Discrepancy-Aware Graph Mask Auto-Encoder Discrepancy-Aware Graph Mask Auto-Encoder KDD 2025
- Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing
- TMLR 2025: Heterophily-informed Message Passing Heterophily-informed Message Passing TMLR 2025
- ICML 2025: Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks ICML 2025
- On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning
- NeurIPS 2024: Even Sparser Graph Transformers Even Sparser Graph Transformers NeurIPS 2024
- NeurIPS 2024: Distributed-Order Fractional Graph Operating Network Distributed-Order Fractional Graph Operating Network NeurIPS 2024
- NeurIPS 2024: Unitary convolutions for learning on graphs and groups Unitary convolutions for learning on graphs and groups NeurIPS 2024
- Re-evaluating the Advancements of Heterophilic Graph Learning Re-evaluating the Advancements of Heterophilic Graph Learning
- HyperAggregation: Aggregating over Graph Edges with Hypernetworks HyperAggregation: Aggregating over Graph Edges with Hypernetworks
- TopoBench: A Framework for Benchmarking Topological Deep Learning TopoBench: A Framework for Benchmarking Topological Deep Learning
- Differentiable Cluster Graph Neural Network Differentiable Cluster Graph Neural Network
- Bundle Neural Networks for message diffusion on graphs Bundle Neural Networks for message diffusion on graphs
- TMLR 2024: Contextualized Messages Boost Graph Representations Contextualized Messages Boost Graph Representations TMLR 2024
- ICLR 2024: Polynormer: Polynomial-Expressive Graph Transformer in Linear Time Polynormer: Polynomial-Expressive Graph Transformer in Linear Time ICLR 2024
- KDD 2024: Graph Mamba: Towards Learning on Graphs with State Space Models Graph Mamba: Towards Learning on Graphs with State Space Models KDD 2024
- ICML 2023: Evolving Computation Graphs Evolving Computation Graphs ICML 2023
- IJCAI 2023: Graph Neural Convection-Diffusion with Heterophily Graph Neural Convection-Diffusion with Heterophily IJCAI 2023
- Graph Neural Networks for Graphs with Heterophily: A Survey Graph Neural Networks for Graphs with Heterophily: A Survey
Binary node classification Synthetic Minesweeper grid graph binary node classification from the heterophilic benchmark. Uses the corrected benchmark features and ten official splits. Evaluated by ROC-AUC.
Dataset details
Task
Synthetic Minesweeper grid graph binary node classification from the heterophilic benchmark. The primary catalog metric is ROC-AUC.
Data
Synthetic Minesweeper grid graph binary node classification from the heterophilic benchmark.
Features
The benchmark provides one fixed graph, node features, labels, and ten official splits per dataset. Features are dataset-specific and include text-derived, product, synthetic-grid, or platform-account attributes described by the release.
Splits and evaluation
The catalog records these protocols or variants: Standard split. Evaluation uses ROC-AUC (higher is better). Exact masks or folds must come from the cited release.
Quirks and pitfalls
Use the corrected release and its ten masks. Several tasks are imbalanced and use ROC-AUC rather than accuracy; treating missing relationships as negative evidence or tuning on the test masks invalidates comparison.
Sources
SOTA Progression
new SOTA
matches SOTA at that time
other proposed result
other baseline result
Leaderboard
| # | Model | ROC-AUC ↑ | Accuracy | Paper |
|---|---|---|---|---|
| 1 | BuNN | 0.9899
±
0.0016 | — | |
| 2 | DC-GNN | 0.9850
±
0.0021 | — | |
| 3 | Tango -GPS | 0.9839
±
0.0054 | — | |
| 4 | Tango -GatedGCN | 0.9832
±
0.0059 | — | |
| 5 | Polynormer-r | 0.9746
±
0.0036 | — | |
| 6 | Polynormer + Wideformer | 0.9726
±
0.0001 | — | |
| 7 | Polynormer + Entropy Reg | 0.9720
±
0.0032 | — | |
| 8 | Polynormer | 0.9696
±
0.0052 | — | |
| 9 | Polynormer-v1 | 0.9696
±
0.0052 | — | |
| 10 | Polynormer-v2 | 0.9648
±
0.0037 | — | |
| 11 | D-CDE | 0.9647
±
0.0189 | — | |
| 12 | Schrödinger | 0.9631
±
0.0049 | — | |
| 13 | Lie Unitary GCN | 0.9611
±
0.0010 | — | |
| 14 | Lie UniGCN | 0.9611
±
0.0010 | — | |
| 15 | F-CDE | 0.9604
±
0.0025 | — | |
| 16 | GCN-SSM (Optimal L) | 0.9602
±
0.0052 | — | |
| 17 | CDE-GRAND-GAT | 0.9550
±
0.0523 | — | |
| 18 | CDE | 0.9550
±
0.0523 | — | |
| 19 | CDE-GRAND | 0.9550
±
0.0523 | — | |
| 20 | Graphite | 0.9478
±
0.0041 | — | |
| 21 | ECG-GAT-sep | 0.9452
±
0.0020 | — | |
| 22 | MLP-ECG-GAT-sep | 0.9452
±
0.0020 | — | |
| 23 | MLPBGRL-GAT-sep | 0.9439
±
0.0020 | — | |
| 24 | Unitary GCN | 0.9427
±
0.0058 | — | |
| 25 | UniGCN | 0.9427
±
0.0058 | — | |
| 26 | GCN (LapPE) | 0.9426
±
0.0049 | — | |
| 27 | BGRL-ECG-GAT-sep | 0.9424
±
0.0015 | — | |
| 28 | SIR-GCN | 0.9412
±
0.0042 | — | |
| 29 | ECG-SAGE | 0.9411
±
0.0007 | — | |
| 30 | BGRL-ECG-SAGE | 0.9411
±
0.0007 | — | |
| 31 | MLP-ECG-SAGE | 0.9410
±
0.0008 | — | |
| 32 | PD-GNN | 0.9403
±
0.0045 | — | |
| 33 | MLPBGRL-ECG-SAGE | 0.9401
±
0.0007 | — | |
| 34 | CDE-GraphBel | 0.9398
±
0.0057 | — | |
| 35 | MLP->GNN-ECG-GAT-sep | 0.9397
±
0.0019 | — | |
| 36 | GAT-sep | 0.9391
±
0.0035 | — | |
| 37 | GAT | 0.9391
±
0.0035 | — | |
| 38 | GPS -GCN+Performer (LapPE) | 0.9385
±
0.0041 | — | |
| 39 | MLP->GNN-ECG-SAGE | 0.9377
±
0.0012 | — | |
| 40 | ECG-GT-sep | 0.9362
±
0.0027 | — | |
| 41 | MLP-ECG-GT-sep | 0.9362
±
0.0027 | — | |
| 42 | BGRL-ECG-GT-sep | 0.9355
±
0.0018 | — | |
| 43 | MLPBGRL-GT-sep | 0.9352
±
0.0025 | — | |
| 44 | GraphGPS + Wideformer | 0.9352
±
0.0007 | — | |
| 45 | GraphSAGE | 0.9351
±
0.0057 | — | |
| 46 | SAGE | 0.9351
±
0.0057 | — | |
| 47 | GAT (LapPE) | 0.9350
±
0.0054 | — | |
| 48 | GraphGPS+Entropy Reg | 0.9335
±
0.0023 | — | |
| 49 | GraphGPS | 0.9326
±
0.0010 | — | |
| 50 | MLP->GNN-ECG-GT-sep | 0.9269
±
0.0034 | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time