Heterophilic Graphs
Cornell
Structure
1Graphs
183Nodes
295Edges
5Classes
1703Node Feature Dim
0.3Homophily
Coverage
751Results
1Variants
120Papers
- Graph Navier–Stokes Networks Graph Navier–Stokes Networks
- ICML 2026: Learning Graph Foundation Models on Riemannian Graph-of-Graphs Learning Graph Foundation Models on Riemannian Graph-of-Graphs ICML 2026
- From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph 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
- Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow
- $P^2$GNN: Two Prototype Sets to boost GNN Performance $P^2$GNN: Two Prototype Sets to boost GNN Performance
- HopFormer: Sparse Graph Transformers with Explicit Receptive Field Control HopFormer: Sparse Graph Transformers with Explicit Receptive Field Control
- 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
- LoG 2025: Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization? Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization? LoG 2025
- Gauge-Equivariant Graph Networks via Self-Interference Cancellation Gauge-Equivariant Graph Networks via Self-Interference Cancellation
- LoG 2025: Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion LoG 2025
- Adaptive Multi-view Graph Contrastive Learning via Fractional-order Neural Diffusion Networks Adaptive Multi-view Graph Contrastive Learning via Fractional-order Neural Diffusion Networks
- 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
- NeurIPS 2025: Preference-driven Knowledge Distillation for Few-shot Node Classification Preference-driven Knowledge Distillation for Few-shot Node Classification NeurIPS 2025
- NeurIPS 2025: One Prompt Fits All: Universal Graph Adaptation for Pretrained Models One Prompt Fits All: Universal Graph Adaptation for Pretrained Models NeurIPS 2025
- Attention Beyond Neighborhoods: Reviving Transformer for Graph Clustering Attention Beyond Neighborhoods: Reviving Transformer for Graph Clustering
- Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
- Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks
- Memorization in Graph Neural Networks Memorization in Graph Neural Networks
- Aligning the Spectrum: Hybrid Graph Pre-training and Prompt Tuning across Homophily and Heterophily Aligning the Spectrum: Hybrid Graph Pre-training and Prompt Tuning across Homophily and Heterophily
- Aggregation-aware MLP: An Unsupervised Approach for Graph Message-passing Aggregation-aware MLP: An Unsupervised Approach for Graph Message-passing
- TMLR 2025: Bayesian Neighborhood Adaptation for Graph Neural Networks Bayesian Neighborhood Adaptation for Graph Neural Networks TMLR 2025
- Non-Dissipative Graph Propagation for Non-Local Community Detection Non-Dissipative Graph Propagation for Non-Local Community Detection
- KDD 2025: Discrepancy-Aware Graph Mask Auto-Encoder Discrepancy-Aware Graph Mask Auto-Encoder KDD 2025
- ICML 2025: Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification ICML 2025
- 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
- OpenGT: A Comprehensive Benchmark For Graph Transformers OpenGT: A Comprehensive Benchmark For Graph Transformers
- Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning
- ICML 2025: Learn Beneficial Noise as Graph Augmentation Learn Beneficial Noise as Graph Augmentation ICML 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
- Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors
- KDD 2025: Depth-Adaptive Graph Neural Networks via Learnable Bakry-Émery Curvature Depth-Adaptive Graph Neural Networks via Learnable Bakry-Émery Curvature KDD 2025
- NeurIPS 2025: A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs NeurIPS 2025
- AAAI 2024: Graph Structure Refinement with Energy-based Contrastive Learning Graph Structure Refinement with Energy-based Contrastive Learning AAAI 2024
- NeurIPS 2024: Distributed-Order Fractional Graph Operating Network Distributed-Order Fractional Graph Operating Network NeurIPS 2024
- ICLR 2024: When Graph Neural Networks Meet Dynamic Mode Decomposition When Graph Neural Networks Meet Dynamic Mode Decomposition ICLR 2024
- TMLR 2024: SCNode: Spatial and Contextual Coordinates for Graph Representation Learning SCNode: Spatial and Contextual Coordinates for Graph Representation Learning TMLR 2024
- ICML 2024: Diss-l-ECT: Dissecting Graph Data with local Euler Characteristic Transforms Diss-l-ECT: Dissecting Graph Data with local Euler Characteristic Transforms ICML 2024
- Redesigning graph filter-based GNNs to relax the homophily assumption This work was supported in part by the Spanish AEI Grants PID2022-136887NB-I00, PID2023-149457OB-I00, FPU20/05554, the Community of Madrid (Madrid ELLIS Unit), and the NSF under award CCF-2340481. Research was sponsored by the Army Research Office and was accomplished under Grant Number W911NF-17-S-0002. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Office or the U.S. Army or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein. Emails: samuel.rey.escudero@urjc.es, nav@rice.edu, victor.tenorio@urjc.es, segarra@rice.edu, antonio.garcia.marques@urjc.es Redesigning graph filter-based GNNs to relax the homophily assumption This work was supported in part by the Spanish AEI Grants PID2022-136887NB-I00, PID2023-149457OB-I00, FPU20/05554, the Community of Madrid (Madrid ELLIS Unit), and the NSF under award CCF-2340481. Research was sponsored by the Army Research Office and was accomplished under Grant Number W911NF-17-S-0002. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Office or the U.S. Army or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein. Emails: samuel.rey.escudero@urjc.es, nav@rice.edu, victor.tenorio@urjc.es, segarra@rice.edu, antonio.garcia.marques@urjc.es
- Disentangled Generative Graph Representation Learning Disentangled Generative Graph Representation Learning
- Graph Triple Attention Network: A Decoupled Perspective Graph Triple Attention Network: A Decoupled Perspective
- Scalable Graph Compressed Convolutions Scalable Graph Compressed Convolutions
- ICLR 2024: The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited ICLR 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
- Graph Neural Reaction Diffusion Models Submitted to the editors June 2023. Accepted in March 2024. Graph Neural Reaction Diffusion Models Submitted to the editors June 2023. Accepted in March 2024.
- ICLR 2024: Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs ICLR 2024
- NeurIPS 2024: Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models NeurIPS 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
- Differentiable Cluster Graph Neural Network Differentiable Cluster Graph Neural Network
- LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework
- Oversmoothing alleviation in graph neural networks: a survey and unified view Oversmoothing alleviation in graph neural networks: a survey and unified view
- Graph Neural Aggregation-diffusion with Metastability Graph Neural Aggregation-diffusion with Metastability
- Simplified PCNet with Robustness Simplified PCNet with Robustness
- Provable Filter for Real-world Graph Clustering Provable Filter for Real-world Graph Clustering
- CDC: A Simple Framework for Complex Data Clustering CDC: A Simple Framework for Complex Data Clustering
- KDD 2024: Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory KDD 2024
- Smoothed Graph Contrastive Learning via Seamless Proximity Integration Smoothed Graph Contrastive Learning via Seamless Proximity Integration
- Design your own universe: a physics-informed agnostic method for enhancing graph neural networks Design your own universe: a physics-informed agnostic method for enhancing graph neural networks
- CAT: A Causal Graph Attention Network for Trimming Heterophilic Graphs CAT: A Causal Graph Attention Network for Trimming Heterophilic Graphs
- 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
- Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification
- ICLR 2023: Effective Structural Encodings via Local Curvature Profiles Effective Structural Encodings via Local Curvature Profiles ICLR 2023
- Dirichlet Energy Enhancement of Graph Neural Networks by Framelet Augmentation Dirichlet Energy Enhancement of Graph Neural Networks by Framelet Augmentation
- NeurIPS 2023: Simple and Asymmetric Graph Contrastive Learning without Augmentations Simple and Asymmetric Graph Contrastive Learning without Augmentations NeurIPS 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
- Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature
- Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning
- Unifying over-smoothing and over-squashing in graph neural networks: A physics informed approach and beyond Unifying over-smoothing and over-squashing in graph neural networks: A physics informed approach and beyond
- Contrastive Learning for Non-Local Graphs with Multi-Resolution Structural Views Contrastive Learning for Non-Local Graphs with Multi-Resolution Structural Views
- ICLR 2023: VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs ICLR 2023
- ICML 2023: Half-Hop: A graph upsampling approach for slowing down message passing Half-Hop: A graph upsampling approach for slowing down message passing ICML 2023
- ICML 2023: Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication ICML 2023
- On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks
- ICML 2023: Towards Deep Attention in Graph Neural Networks: Problems and Remedies Towards Deep Attention in Graph Neural Networks: Problems and Remedies ICML 2023
- IJCAI 2023: Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention IJCAI 2023
- Multi-View Graph Representation Learning Beyond Homophily Multi-View Graph Representation Learning Beyond Homophily
- LON-GNN: Spectral GNNs with Learnable Orthonormal Basis LON-GNN: Spectral GNNs with Learnable Orthonormal Basis
- WWW 2023: SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization WWW 2023
- Steering Graph Neural Networks with Pinning Control Steering Graph Neural Networks with Pinning Control
- Framelet Message Passing Framelet Message Passing
- Heterophily-Aware Graph Attention Network Heterophily-Aware Graph Attention Network
- Node-oriented Spectral Filtering for Graph Neural Networks Node-oriented Spectral Filtering for Graph Neural Networks
- 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
- NeurIPS 2022: Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again NeurIPS 2022
- ICLR 2022: Gradient Gating for Deep Multi-Rate Learning on Graphs Gradient Gating for Deep Multi-Rate Learning on Graphs ICLR 2022
- GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials
- Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks
- ICML 2022: Optimization-Induced Graph Implicit Nonlinear Diffusion Optimization-Induced Graph Implicit Nonlinear Diffusion ICML 2022
- TMLR 2022: Understanding convolution on graphs via energies Understanding convolution on graphs via energies TMLR 2022
- ICLR 2022: ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks ICLR 2022
- Decoupled Self-supervised Learning for Non-Homophilou Graphs Decoupled Self-supervised Learning for Non-Homophilou Graphs
- AAAI 2022: Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering Restructuring Graphs for Higher Homophily via Adaptive Spectral Clustering AAAI 2022
- ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting
- TMLR 2022: Simplifying Node Classification on Heterophilous Graphs with Compatible Label Propagation Simplifying Node Classification on Heterophilous Graphs with Compatible Label Propagation TMLR 2022
- ICML 2022: Finding Global Homophily in Graph Neural Networks When Meeting Heterophily Finding Global Homophily in Graph Neural Networks When Meeting Heterophily ICML 2022
- ICLR 2022: Graph Auto-Encoder Via Neighborhood Wasserstein Reconstruction Graph Auto-Encoder Via Neighborhood Wasserstein Reconstruction ICLR 2022
- NeurIPS 2022: Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited NeurIPS 2022
- ICML 2022: Graph-Coupled Oscillator Networks Graph-Coupled Oscillator Networks ICML 2022
- A Piece-wise Polynomial Filtering Approach for Graph Neural Networks A Piece-wise Polynomial Filtering Approach for Graph Neural Networks
- Simplifying approach to Node Classification in Graph Neural Networks Simplifying approach to Node Classification in Graph Neural Networks
- WWW 2021: GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily WWW 2021
- Label-Wise Graph Convolutional Network for Heterophilic Graphs Label-Wise Graph Convolutional Network for Heterophilic Graphs
- AAAI 2021: Graph Pointer Neural Networks Graph Pointer Neural Networks AAAI 2021
- Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study
- 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
- ICML 2021: Graph Neural Networks Inspired by Classical Iterative Algorithms Graph Neural Networks Inspired by Classical Iterative Algorithms ICML 2021
- NCGNN: Node-Level Capsule Graph Neural Network for Semisupervised Classification NCGNN: Node-Level Capsule Graph Neural Network for Semisupervised Classification
- NeurIPS 2020: Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks NeurIPS 2020
- Non-Local Graph Neural Networks Non-Local Graph Neural Networks
5-class node classification WebKB node classification on Cornell university webpages (5 classes). Uses the Geom-GCN/PyG node features and graph. Evaluated by Accuracy.
Dataset details
Task
WebKB node classification on Cornell university webpages (5 classes). The primary catalog metric is Accuracy.
Data
WebKB node classification on Cornell 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 ↑ | Avg MemScore | Conductance | F1 | MR | Micro-F1 | NMI | Paper |
|---|---|---|---|---|---|---|---|---|---|
| 1 | P^2GNN | 0.9541
±
0.0272 | — | — | — | — | — | — | |
| 2 | ACM-GCN | 0.9480
±
0.0380 | — | — | — | — | — | — | |
| 3 | RF-GCN | 0.9429 | — | — | — | — | — | — | |
| 4 | SPCNet-D | 0.9425
±
0.0192 | — | — | — | — | — | — | Simplified PCNet with Robustness
no code |
| 5 | FMP ode | 0.9380
±
0.0150 | — | — | — | — | — | — | Framelet Message Passing
no code |
| 6 | SPCNet-L | 0.9362
±
0.0213 | — | — | — | — | — | — | Simplified PCNet with Robustness
no code |
| 7 | general Bayesian inference strategy + GCNII | 0.9361
±
0.0213 | — | — | — | — | — | — | |
| 8 | HA-GAT | 0.9344
±
0.0284 | — | — | — | — | — | — | |
| 9 | OptBasisGNN | 0.9299
±
0.0185 | — | — | — | — | — | — | Simplified PCNet with Robustness
no code |
| 10 | JacobiConv | 0.9295
±
0.0246 | — | — | — | — | — | — | |
| 11 | RDGNN-I | 0.9272
±
0.0588 | — | — | — | — | — | — | |
| 12 | VR-GNN | 0.9270
±
0.0270 | — | — | — | — | — | — | |
| 13 | RDGNN-S | 0.9243
±
0.0551 | — | — | — | — | — | — | |
| 14 | ChebNetII | 0.9230
±
0.0148 | — | — | — | — | — | — | |
| 15 | BernNet | 0.9213
±
0.0164 | — | — | — | — | — | — | |
| 16 | EvenNet | 0.9213
±
0.0172 | — | — | — | — | — | — | Simplified PCNet with Robustness
no code |
| 17 | Jacobi+Learnable | 0.9191 | — | — | — | — | — | — | |
| 18 | NFGNN | 0.9190
±
0.0091 | — | — | — | — | — | — | |
| 19 | GPR-GNN | 0.9157
±
0.0196 | — | — | — | — | — | — | |
| 20 | APPNP | 0.9152
±
0.0181 | — | — | — | — | — | — | |
| 21 | DMD++ | 0.9140
±
0.0170 | — | — | — | — | — | — | |
| 22 | GPRGNN | 0.9137
±
0.0181 | — | — | — | — | — | — | |
| 23 | G-MHKG | 0.9020
±
0.0090 | — | — | — | — | — | — | |
| 24 | D-GRAND | 0.9000
±
0.0467 | — | — | — | — | — | — | |
| 25 | PDE-GCN | 0.8973
±
0.0135 | — | — | — | — | — | — | |
| 26 | PDE-GCNM | 0.8973 | — | — | — | — | — | — | |
| 27 | D-GREAD | 0.8946
±
0.0426 | — | — | — | — | — | — | |
| 28 | GLGCNII | 0.8919 | — | — | — | — | — | — | |
| 29 | CGP (GCN) | 0.8919 | — | — | — | — | — | — | |
| 30 | GNSN | 0.8919
±
0.0513 | — | — | — | — | — | — | |
| 31 | MM-FGCN | 0.8890
±
0.0830 | — | — | — | — | — | — | |
| 32 | CATv3-sup | 0.8880
±
0.0210 | — | — | — | — | — | — | |
| 33 | RevGAT+T | 0.8846 | — | — | — | — | — | — | |
| 34 | CATv3-semi | 0.8840
±
0.0210 | — | — | — | — | — | — | |
| 35 | DiGGR | 0.8838
±
0.0684 | — | — | — | — | — | — | |
| 36 | DMD-ACMP | 0.8810
±
0.0240 | — | — | — | — | — | — | |
| 37 | SCNode | 0.8809
±
0.0191 | — | — | — | — | — | — | |
| 38 | UYGAT | 0.8740
±
0.0130 | — | — | — | — | — | — | |
| 39 | G2-gating | 0.8730 | — | — | — | — | — | — | |
| 40 | G^2-GAT | 0.8730
±
0.0484 | — | — | — | — | — | — | |
| 41 | FSGNN (Homo/Hetero) 3-hop | 0.8730
±
0.0593 | — | — | — | — | — | — | |
| 42 | FSGNN (Homo/Hetero) 8-hop | 0.8730
±
0.0453 | — | — | — | — | — | — | |
| 43 | G2 | 0.8730
±
0.0484 | — | — | — | — | — | — | |
| 44 | SAGE+T | 0.8718 | — | — | — | — | — | — | |
| 45 | Ord. GNN | 0.8703
±
0.0470 | — | — | — | — | — | — | |
| 46 | OGNN | 0.8703
±
0.0473 | — | — | — | — | — | — | |
| 47 | GREAD | 0.8703
±
0.0495 | — | — | — | — | — | — | |
| 48 | DMP | 0.8700
±
0.0552 | — | — | — | — | — | — | |
| 49 | ASGAT | 0.8690
±
0.0420 | — | — | — | — | — | — | Framelet Message Passing
no code |
| 50 | F-GREAD | 0.8689
±
0.0416 | — | — | — | — | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time