Heterophilic Graphs
Actor
Structure
1Graphs
7,600Nodes
29,926Edges
5Classes
931Node Feature Dim
0.22Homophily
Coverage
708Results
1Variants
113Papers
- Graph Navier–Stokes Networks Graph Navier–Stokes Networks
- 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
- WWW 2026: Frequency-Corrupt Based Graph Self-Supervised Learning Frequency-Corrupt Based Graph Self-Supervised Learning WWW 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
- SPGCL: Simple yet Powerful Graph Contrastive Learning via SVD-Guided Structural Perturbation SPGCL: Simple yet Powerful Graph Contrastive Learning via SVD-Guided Structural Perturbation
- GADPN: Graph Adaptive Denoising and Perturbation Networks via Singular Value Decomposition GADPN: Graph Adaptive Denoising and Perturbation Networks via Singular Value Decomposition
- mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks
- ICML 2025: View Space: Learning Representation across Arbitrary Graphs View Space: Learning Representation across Arbitrary Graphs ICML 2025
- 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 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
- Toward General Digraph Contrastive Learning: A Dual Spatial Perspective Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
- NeurIPS 2025: One Prompt Fits All: Universal Graph Adaptation for Pretrained Models One Prompt Fits All: Universal Graph Adaptation for Pretrained Models NeurIPS 2025
- Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
- 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
- Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax
- KDD 2025: Discrepancy-Aware Graph Mask Auto-Encoder Discrepancy-Aware Graph Mask Auto-Encoder KDD 2025
- Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models
- Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach
- OpenGT: A Comprehensive Benchmark For Graph Transformers OpenGT: A Comprehensive Benchmark For Graph Transformers
- IJCAI 2025: What Can We Learn From MIMO Graph Convolutions? What Can We Learn From MIMO Graph Convolutions? IJCAI 2025
- IJCAI 2025: Rethinking Graph Contrastive Learning through Relative Similarity Preservation Rethinking Graph Contrastive Learning through Relative Similarity Preservation IJCAI 2025
- TMLR 2025: Piecewise Constant Spectral Graph Neural Network Piecewise Constant Spectral Graph Neural Network TMLR 2025
- WWW 2025: Graph Wave Networks Graph Wave Networks WWW 2025
- Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors
- TMLR 2025: Diffusion on Graph: Augmentation of Graph Structure for Node Classification Diffusion on Graph: Augmentation of Graph Structure for Node Classification TMLR 2025
- TMLR 2025: A Fused Gromov-Wasserstein Approach to Subgraph Contrastive Learning A Fused Gromov-Wasserstein Approach to Subgraph Contrastive Learning TMLR 2025
- Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphs Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphs
- On the Cross-type Homophily of Heterogeneous Graphs: Understanding and Unleashing On the Cross-type Homophily of Heterogeneous Graphs: Understanding and Unleashing
- AAAI 2024: Graph Structure Refinement with Energy-based Contrastive Learning Graph Structure Refinement with Energy-based Contrastive Learning AAAI 2024
- ICML 2024: GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers ICML 2024
- NeurIPS 2024: Even Sparser Graph Transformers Even Sparser Graph Transformers NeurIPS 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
- Disentangled Generative Graph Representation Learning Disentangled Generative Graph Representation Learning
- WWW 2024: Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts WWW 2024
- Graph Triple Attention Network: A Decoupled Perspective Graph Triple Attention Network: A Decoupled Perspective
- Scalable Graph Compressed Convolutions Scalable Graph Compressed Convolutions
- 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
- 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
- HyperAggregation: Aggregating over Graph Edges with Hypernetworks HyperAggregation: Aggregating over Graph Edges with Hypernetworks
- 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
- 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.
- NeurIPS 2024: ProG: A Graph Prompt Learning Benchmark ProG: A Graph Prompt Learning Benchmark NeurIPS 2024
- Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach
- NeurIPS 2024: Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models NeurIPS 2024
- ICML 2024: What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding ICML 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
- 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
- Graph Neural Aggregation-diffusion with Metastability Graph Neural Aggregation-diffusion with Metastability
- ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks
- WWW 2024: Optimizing Polynomial Graph Filters: A Novel Adaptive Krylov Subspace Approach Optimizing Polynomial Graph Filters: A Novel Adaptive Krylov Subspace Approach WWW 2024
- Simplified PCNet with Robustness Simplified PCNet with Robustness
- 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
- ICLR 2024: Graph Parsing Networks Graph Parsing Networks ICLR 2024
- 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
- NeurIPS 2023: Simple and Asymmetric Graph Contrastive Learning without Augmentations Simple and Asymmetric Graph Contrastive Learning without Augmentations NeurIPS 2023
- Spectral-Aware Augmentation for Enhanced Graph Representation Learning Spectral-Aware Augmentation for Enhanced Graph Representation Learning
- WWW 2023: A Quasi-Wasserstein Loss for Learning Graph Neural Networks A Quasi-Wasserstein Loss for Learning Graph Neural Networks WWW 2023
- SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning
- NeurIPS 2023: GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation NeurIPS 2023
- Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning
- Contrastive Learning for Non-Local Graphs with Multi-Resolution Structural Views Contrastive Learning for Non-Local Graphs with Multi-Resolution Structural Views
- AAAI 2023: Feature Transportation Improves Graph Neural Networks Feature Transportation Improves Graph Neural Networks AAAI 2023
- Frameless Graph Knowledge Distillation Frameless Graph Knowledge Distillation
- 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
- 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
- ICML 2023: Feature Expansion for Graph Neural Networks Feature Expansion for Graph Neural Networks ICML 2023
- 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
- Graph Contrastive Learning under Heterophily via Graph Filters Graph Contrastive Learning under Heterophily via Graph Filters
- Steering Graph Neural Networks with Pinning Control Steering Graph Neural Networks with Pinning Control
- ICML 2023: Graph Neural Networks with Learnable and Optimal Polynomial Bases Graph Neural Networks with Learnable and Optimal Polynomial Bases ICML 2023
- WWW 2023: Homophily-oriented Heterogeneous Graph Rewiring Homophily-oriented Heterogeneous Graph Rewiring WWW 2023
- Heterophily-Aware Graph Attention Network Heterophily-Aware Graph Attention Network
- Localized Graph Contrastive Learning Localized Graph Contrastive Learning
- 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: Hierarchical Graph Transformer with Adaptive Node Sampling Hierarchical Graph Transformer with Adaptive Node Sampling NeurIPS 2022
- ICLR 2022: Gradient Gating for Deep Multi-Rate Learning on Graphs Gradient Gating for Deep Multi-Rate Learning on Graphs ICLR 2022
- Graph Soft-Contrastive Learning via Neighborhood Ranking Graph Soft-Contrastive Learning via Neighborhood Ranking
- Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks
- Deformable Graph Transformer Deformable Graph Transformer
- TMLR 2022: Understanding convolution on graphs via energies Understanding convolution on graphs via energies TMLR 2022
- 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
- Augmentation-Free Graph Contrastive Learning with Performance Guarantee Augmentation-Free Graph Contrastive Learning with Performance Guarantee
- TMLR 2022: Unsupervised Network Embedding Beyond Homophily Unsupervised Network Embedding Beyond Homophily TMLR 2022
- NeurIPS 2022: Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited NeurIPS 2022
- Graph Representation Learning via Aggregation Enhancement Graph Representation Learning via Aggregation Enhancement
- Simplifying approach to Node Classification in Graph Neural Networks Simplifying approach to Node Classification in Graph Neural Networks
- 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
- ICML 2021: Graph Neural Networks Inspired by Classical Iterative Algorithms Graph Neural Networks Inspired by Classical Iterative Algorithms ICML 2021
- AAAI 2021: Beyond Low-frequency Information in Graph Convolutional Networks Beyond Low-frequency Information in Graph Convolutional Networks AAAI 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
- ICLR 2020: Heterophilic Graphs Heterophilic Graphs ICLR 2020
5-class node classification Actor co-occurrence node classification (5 classes) from the Geom-GCN paper. Uses the Geom-GCN/PyG node features and graph. Evaluated by Accuracy.
Dataset details
Task
Actor co-occurrence node classification (5 classes) from the Geom-GCN paper. Also called Film in papers using the same graph. The primary catalog metric is Accuracy.
Data
Actor co-occurrence node classification (5 classes) from the Geom-GCN paper. Also called Film in papers using the same graph.
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 ↑ | ACC (clustering accuracy) | ACC (node clustering accuracy) | Accuracy (micro F1 per L1108) | Avg MemScore | F1 | MR | Macro-F1 | Micro-F1 | ROC-AUC | Paper |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | DiGGR | 0.4535
±
0.0353 | — | — | — | — | — | — | — | — | — | |
| 2 | TRIGON | 0.4402
±
0.0028 | — | — | — | — | — | — | — | — | — | |
| 3 | DoG | 0.4320
±
0.0120 | — | — | — | — | — | — | — | — | — | |
| 4 | FavardGNN | 0.4305
±
0.0053 | — | — | — | — | — | — | — | — | — | |
| 5 | P^2GNN | 0.4305
±
0.0134 | — | — | — | — | — | — | — | — | — | |
| 6 | UniAug - PolyGCL | 0.4301
±
0.0127 | — | — | — | — | — | — | — | — | — | |
| 7 | GrokFormer | 0.4298
±
0.0148 | — | — | — | — | — | — | — | — | — | |
| 8 | AdaptKry | 0.4270
±
0.0114 | — | — | — | — | — | — | — | — | — | |
| 9 | SpatUFG | 0.4250
±
0.0019 | — | — | — | — | — | — | — | — | — | |
| 10 | FMLP-O | 0.4250
±
0.0011 | — | — | — | — | — | — | — | — | — | |
| 11 | OptBasisGNN | 0.4239
±
0.0052 | — | — | — | — | — | — | — | — | — | |
| 12 | HEI | 0.4225
±
0.0159 | — | — | — | — | — | — | — | — | — | |
| 13 | HA-GAT(M) | 0.4216
±
0.0114 | — | — | — | — | — | — | — | — | — | |
| 14 | VR-GNN | 0.4216
±
0.0042 | — | — | — | — | — | — | — | — | — | |
| 15 | GWN-fa | 0.4203
±
0.0159 | — | — | — | — | — | — | — | — | — | |
| 16 | GNN-LF | 0.4197
±
0.0006 | — | — | — | — | — | — | — | — | — | |
| 17 | FC-GSSL | 0.4194
±
0.0092 | — | — | — | — | — | — | — | — | — | |
| 18 | Specformer | 0.4193
±
0.0104 | — | — | — | — | — | — | — | — | — | |
| 19 | HiGCN | 0.4181
±
0.0052 | — | — | — | — | — | — | — | — | — | |
| 20 | ChebNetII | 0.4175
±
0.0107 | — | — | — | — | — | — | — | — | — | |
| 21 | BernNet | 0.4171
±
0.0112 | — | — | — | — | — | — | — | — | — | |
| 22 | SGFormer | 0.4169
±
0.0063 | — | — | — | — | — | — | — | — | — | |
| 23 | Free eigenvalues | 0.4161
±
0.0063 | — | — | — | — | — | — | — | — | — | |
| 24 | ACM-GCN | 0.4160
±
0.0110 | — | — | — | — | — | — | — | — | — | |
| 25 | CaNet | 0.4158
±
0.0132 | — | — | — | — | — | — | — | — | — | |
| 26 | IENE | 0.4158
±
0.0137 | — | — | — | — | — | — | — | — | — | |
| 27 | FLOOD | 0.4154
±
0.0134 | — | — | — | — | — | — | — | — | — | |
| 28 | PolyFormer | 0.4151
±
0.0071 | — | — | — | — | — | — | — | — | — | |
| 29 | QW | 0.4137
±
0.0067 | — | — | — | — | — | — | — | — | — | |
| 30 | DR | 0.4136
±
0.0020 | — | — | — | — | — | — | — | — | — | |
| 31 | FMLP-S | 0.4130
±
0.0024 | — | — | — | — | — | — | — | — | — | |
| 32 | BAGNN | 0.4126
±
0.0152 | — | — | — | — | — | — | — | — | — | |
| 33 | SIGN | 0.4122
±
0.0096 | — | — | — | — | — | — | — | — | — | |
| 34 | JacobiConv | 0.4117
±
0.0064 | — | — | — | — | — | — | — | — | — | |
| 35 | PolyGCL | 0.4115
±
0.0088 | — | — | — | — | — | — | — | — | — | |
| 36 | ERM | 0.4096
±
0.0152 | — | — | — | — | — | — | — | — | — | |
| 37 | SPCNet-D | 0.4089
±
0.0061 | — | — | — | — | — | — | — | — | — | Simplified PCNet with Robustness
no code |
| 38 | NFGNN | 0.4062
±
0.0038 | — | — | — | — | — | — | — | — | — | |
| 39 | EvenNet | 0.4048
±
0.0062 | — | — | — | — | — | — | — | — | — | Simplified PCNet with Robustness
no code |
| 40 | SPCNet-L | 0.4023
±
0.0070 | — | — | — | — | — | — | — | — | — | Simplified PCNet with Robustness
no code |
| 41 | MLP | 0.4018
±
0.0055 | — | — | — | — | — | — | — | — | — | |
| 42 | UniFilter | 0.4011
±
0.0131 | — | — | — | — | — | — | — | — | — | |
| 43 | GT | 0.4010 | — | — | — | — | — | — | — | — | — | |
| 44 | ZLHL | 0.4010 | — | — | — | — | — | — | — | — | — | |
| 45 | ANS-GT | 0.4010
±
0.0112 | — | — | — | — | — | — | — | — | — | |
| 46 | SUFG | 0.4010
±
0.0020 | — | — | — | — | — | — | — | — | — | |
| 47 | NAGphormer | 0.4008
±
0.0150 | — | — | — | — | — | — | — | — | — | |
| 48 | BernNet | 0.4001
±
0.0042 | — | — | — | — | — | — | — | — | — | |
| 49 | GWN-sym | 0.3997
±
0.0172 | — | — | — | — | — | — | — | — | — | |
| 50 | Transformer | 0.3995
±
0.0064 | — | — | — | — | — | — | — | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time