Heterophilic Graphs
Wisconsin
Structure
1Graphs
251Nodes
499Edges
5Classes
1703Node Feature Dim
0.21Homophily
Coverage
284Results
1Variants
38Papers
- Graph Navier–Stokes Networks Graph Navier–Stokes Networks
- 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
- Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow
- Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms
- GraIP: A Benchmarking Framework For Neural Graph Inverse Problems GraIP: A Benchmarking Framework For Neural Graph Inverse Problems
- Gauge-Equivariant Graph Networks via Self-Interference Cancellation Gauge-Equivariant Graph Networks via Self-Interference Cancellation
- Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models
- ICLR 2025: Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing ICLR 2025
- Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models
- IJCAI 2025: What Can We Learn From MIMO Graph Convolutions? What Can We Learn From MIMO Graph Convolutions? IJCAI 2025
- TMLR 2025: Heterophily-informed Message Passing Heterophily-informed Message Passing TMLR 2025
- KDD 2025: GCoT: Chain-of-Thought Prompt Learning for Graphs GCoT: Chain-of-Thought Prompt Learning for Graphs KDD 2025
- ICLR 2024: When Graph Neural Networks Meet Dynamic Mode Decomposition When Graph Neural Networks Meet Dynamic Mode Decomposition ICLR 2024
- Disentangled Generative Graph Representation Learning Disentangled Generative Graph Representation Learning
- Graph Triple Attention Network: A Decoupled Perspective Graph Triple Attention Network: A Decoupled Perspective
- TMLR 2024: GraphFM: A generalist graph transformer that learns transferable representations across diverse domains GraphFM: A generalist graph transformer that learns transferable representations across diverse domains TMLR 2024
- KDD 2024: The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs KDD 2024
- Global-Local Graph Neural Networks for Node-Classification Global-Local Graph Neural Networks for Node-Classification
- ICML 2024: Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs ICML 2024
- 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
- LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework
- ICLR 2024: Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND ICLR 2024
- AAAI 2023: Curriculum-Enhanced Residual Soft An-Isotropic Normalization for Over-smoothness in Deep GNNs Curriculum-Enhanced Residual Soft An-Isotropic Normalization for Over-smoothness in Deep GNNs AAAI 2023
- ICLR 2023: Effective Structural Encodings via Local Curvature Profiles Effective Structural Encodings via Local Curvature Profiles ICLR 2023
- ICML 2023: Graph Neural Networks with a Distribution of Parametrized Graphs Graph Neural Networks with a Distribution of Parametrized Graphs ICML 2023
- TMLR 2023: Non-backtracking Graph Neural Networks Non-backtracking Graph Neural Networks TMLR 2023
- GraphText: Graph Reasoning in Text Space GraphText: Graph Reasoning in Text Space
- Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning
- ICML 2023: Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication ICML 2023
- IJCAI 2023: Graph Neural Convection-Diffusion with Heterophily Graph Neural Convection-Diffusion with Heterophily IJCAI 2023
- ICML 2022: TIDE: Time Derivative Diffusion for Deep Learning on Graphs TIDE: Time Derivative Diffusion for Deep Learning on Graphs ICML 2022
- AAAI 2022: Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating AAAI 2022
- From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm
- ICML 2022: Optimization-Induced Graph Implicit Nonlinear Diffusion Optimization-Induced Graph Implicit Nonlinear Diffusion ICML 2022
- AAAI 2022: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering AAAI 2022
- ICLR 2021: Is Homophily a Necessity for Graph Neural Networks? Is Homophily a Necessity for Graph Neural Networks? ICLR 2021
- Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
- Non-Local Graph Neural Networks Non-Local Graph Neural Networks
5-class node classification WebKB node classification on Wisconsin university webpages (5 classes). Uses the Geom-GCN/PyG node features and graph. Evaluated by Accuracy.
Dataset details
Task
WebKB node classification on Wisconsin university webpages (5 classes). The primary catalog metric is Accuracy.
Data
WebKB node classification on Wisconsin university webpages (5 classes).
Features
Features and edges follow the Geom-GCN/PyG artifact: WebKB uses webpage bag-of-words and hyperlinks, Actor uses film-page keywords and co-occurrence links, and WikipediaNetwork uses page features and hyperlinks.
Splits and evaluation
The catalog records these protocols or variants: Standard split. Evaluation uses Accuracy (higher is better). Exact masks or folds must come from the cited release.
Quirks and pitfalls
These small or repurposed graphs have contested preprocessing and split conventions. Results across Geom-GCN, PyG, and corrected heterophily artifacts are not automatically comparable; class imbalance and high variance require multiple splits.
Sources
Geom-GCN 10 fixed splits.
SOTA Progression
new SOTA
matches SOTA at that time
other proposed result
other baseline result
Leaderboard
| # | Model | Accuracy ↑ | F1 | Micro-F1 | Paper |
|---|---|---|---|---|---|
| 1 | DMD++ | 0.9190
±
0.0260 | — | — | |
| 2 | F-GREAD-BS | 0.9059
±
0.0380 | — | — | |
| 3 | APPNP | 0.9010
±
0.0350 | — | — | |
| 4 | GNSN | 0.9002
±
0.0194 | — | — | |
| 5 | GLGCNII | 0.8972 | — | — | |
| 6 | GREAD-BS | 0.8941
±
0.0330 | — | — | |
| 7 | Sheaf | 0.8941
±
0.0474 | — | — | |
| 8 | GREAD | 0.8941
±
0.0130 | — | — | |
| 9 | DMD-ACMP | 0.8940
±
0.0220 | — | — | |
| 10 | M2M-GNN | 0.8901
±
0.0410 | — | — | |
| 11 | Framelets | 0.8890
±
0.0320 | — | — | |
| 12 | GRAND | 0.8860
±
0.0210 | — | — | |
| 13 | MM-FGCN | 0.8850
±
0.0410 | — | — | |
| 14 | ACM-GCN | 0.8843
±
0.0322 | — | — | |
| 15 | MUSE | 0.8824
±
0.0320 | — | — | |
| 16 | LRGNN | 0.8823
±
0.0354 | — | — | |
| 17 | GNRF | 0.8820
±
0.0384 | — | — | |
| 18 | GIND | 0.8804
±
0.0397 | — | — | |
| 19 | Ord. GNN | 0.8804
±
0.0360 | — | — | |
| 20 | OGNN | 0.8804
±
0.0363 | — | — | |
| 21 | GCON | 0.8780
±
0.0330 | — | — | |
| 22 | GRAFF | 0.8745
±
0.0294 | — | — | |
| 23 | NLMLP | 0.8730
±
0.0430 | — | — | Non-Local Graph Neural Networks
no code |
| 24 | DiGGR | 0.8725
±
0.0441 | — | — | |
| 25 | GloGNN | 0.8706
±
0.0353 | — | — | |
| 26 | EM-ACM | 0.8706
±
0.0251 | — | — | |
| 27 | WRGAT | 0.8698
±
0.0378 | — | — | |
| 28 | GOAL | 0.8698
±
0.0440 | — | — | |
| 29 | de_attn + ada_inte | 0.8695 | — | — | |
| 30 | EIGNN | 0.8686
±
0.0554 | — | — | |
| 31 | GGCN | 0.8686
±
0.0329 | — | — | |
| 32 | H_2GCN | 0.8670
±
0.0470 | — | — | Non-Local Graph Neural Networks
no code |
| 33 | H2GCN-1 | 0.8667
±
0.0469 | — | — | |
| 34 | MLP + GCN | 0.8643
±
0.0400 | — | — | |
| 35 | ACMP | 0.8610
±
0.0400 | — | — | |
| 36 | H2GCN | 0.8588
±
0.0458 | — | — | |
| 37 | H2GCN-2 | 0.8588
±
0.0422 | — | — | |
| 38 | HopGNN | 0.8569
±
0.0543 | — | — | |
| 39 | SimP-GCN | 0.8550 | — | — | Non-Local Graph Neural Networks
no code |
| 40 | PloyGCL | 0.8550
±
0.0188 | — | — | |
| 41 | GPRGNN | 0.8550
±
0.0500 | — | — | |
| 42 | MLP LO | 0.8528
±
0.0588 | — | — | |
| 43 | DMD-GCN | 0.8520
±
0.0210 | — | — | |
| 44 | GREET | 0.8490 | — | — | |
| 45 | MLP | 0.8490
±
0.0530 | — | — | Non-Local Graph Neural Networks
no code |
| 46 | R-SoftGraphAIN | 0.8471
±
0.0088 | — | — | |
| 47 | CPGNN-MLP | 0.8458
±
0.0272 | — | — | |
| 48 | ARMA | 0.8450
±
0.0030 | — | — | |
| 49 | GraphSAGE+mix. | 0.8450
±
0.0110 | — | — | |
| 50 | de_attn + c_inte | 0.8449 | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time