| Evolution of Graph Classifiers | ✓ Link | 100.00% | 100 | | | Evolution of Graph Classifiers | 2019-10-04 |
| Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks | ✓ Link | 96.66% | | | | MEWISPool | 2021-07-03 |
| Template based Graph Neural Network with Optimal Transport Distances | ✓ Link | 96.4% | | | | TFGW ADJ (L=2) | 2022-05-31 |
| Graph isomorphism UNet | ✓ Link | 95.7% | | | | GIUNet | 2023-08-23 |
| When Work Matters: Transforming Classical Network Structures to Graph CNN | | 95.00% | | | | G_Inception | 2018-07-07 |
| Gaussian-Induced Convolution for Graphs | | 94.44% | | | | GIC | 2018-11-11 |
| CIN++: Enhancing Topological Message Passing | ✓ Link | 94.4% | | | | CIN++ | 2023-06-06 |
| Mutual Information Maximization in Graph Neural Networks | ✓ Link | 94.14% | | | | sGIN | 2019-05-21 |
| Cell Attention Networks | ✓ Link | 94.1% | | | | CAN | 2022-09-16 |
| Subgraph Networks with Application to Structural Feature Space Expansion | | 93.68% | | | | Deep WL SGN(0,1,2) | 2019-03-21 |
| Quantum-based subgraph convolutional neural networks | | 93.13% | 93.13 | | | QS-CNNs (Quantum Walk) | 2019-04-01 |
| Learning Convolutional Neural Networks for Graphs | ✓ Link | 92.63% | | | | PATCHY-SAN | 2016-05-17 |
| DDGK: Learning Graph Representations for Deep Divergence Graph Kernels | ✓ Link | 91.58% | | | | DDGK | 2019-04-21 |
| Graph-level Representation Learning with Joint-Embedding Predictive Architectures | ✓ Link | 91.25% | | | | Graph-JEPA | 2023-09-27 |
| Graph Star Net for Generalized Multi-Task Learning | ✓ Link | 91.2% | | | | GraphStar | 2019-06-21 |
| TREE-G: Decision Trees Contesting Graph Neural Networks | ✓ Link | 91.1% | | | | TREE-G | 2022-07-06 |
| Segmented Graph-Bert for Graph Instance Modeling | ✓ Link | 90.85% | | | | SEG-BERT | 2020-02-09 |
| Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification | ✓ Link | 90.84% | | | | GFN | 2019-05-11 |
| Provably Powerful Graph Networks | ✓ Link | 90.55% | | | | PPGN | 2019-05-27 |
| Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation | ✓ Link | 90.44% | | | | GAT-GC (f-Scaled) | 2019-07-04 |
| DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks | ✓ Link | 90.4% | | | | DropGIN | 2021-11-11 |
| A simple yet effective baseline for non-attributed graph classification | ✓ Link | 90.1% | | | | LDP | 2018-11-08 |
| PANDA: Expanded Width-Aware Message Passing Beyond Rewiring | ✓ Link | 90.05% | | | | R-GCN + PANDA | 2024-06-06 |
| Graph Representation Learning via Hard and Channel-Wise Attention Networks | ✓ Link | 90.00% | | | | hGANet | 2019-07-05 |
| Universal Graph Transformer Self-Attention Networks | ✓ Link | 89.97% | | | | U2GNN | 2019-09-26 |
| Factorizable Graph Convolutional Networks | ✓ Link | 89.9% | 89.9% | | | FactorGCN | 2020-10-12 |
| Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification | ✓ Link | 89.89% | | | | GFN-light | 2019-05-11 |
| How Powerful are Graph Neural Networks? | ✓ Link | 89.4% | | | | GIN-0 | 2018-10-01 |
| Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules | ✓ Link | 89.1% | | | | Multigraph ChebNet | 2018-11-23 |
| InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization | ✓ Link | 89.01% | | | | InfoGraph | 2019-07-31 |
| Learning Convolutional Neural Networks for Graphs | ✓ Link | 88.95% | | | | PSCN | 2016-05-17 |
| Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations | | 88.9% | | | | BC + Capsules | 2019-02-22 |
| edGNN: a Simple and Powerful GNN for Directed Labeled Graphs | ✓ Link | 88.8% | | | | edGNN (max) | 2019-04-18 |
| PANDA: Expanded Width-Aware Message Passing Beyond Rewiring | ✓ Link | 88.75% | | | | GIN + PANDA | 2024-06-06 |
| Relation order histograms as a network embedding tool | ✓ Link | 88.68% | | | | NERO | 2021-06-09 |
| Graph Kernels Based on Linear Patterns: Theoretical and Experimental Comparisons | ✓ Link | 88.47% | | | | Path up to length h | 2019-03-01 |
| Universal Graph Transformer Self-Attention Networks | ✓ Link | 88.47% | | | | U2GNN (Unsupervised) | 2019-09-26 |
| Optimal Transport for structured data with application on graphs | ✓ Link | 88.42% | | | | FGW wl h=4 sp | 2018-05-23 |
| A Simple Baseline Algorithm for Graph Classification | ✓ Link | 88.4% | | | | SF + RFC | 2018-10-22 |
| Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs | ✓ Link | 88.33% | | | | ECC (5 scores) | 2017-04-10 |
| Wasserstein Embedding for Graph Learning | ✓ Link | 88.3% | | | | WEGL | 2020-06-16 |
| PANDA: Expanded Width-Aware Message Passing Beyond Rewiring | ✓ Link | 88.2% | | | | R-GIN + PANDA | 2024-06-06 |
| Anonymous Walk Embeddings | ✓ Link | 87.87% | | | | AWE | 2018-05-30 |
| Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks | ✓ Link | 87.7% | | | | Graphlet Kernel | 2018-10-04 |
| DiffWire: Inductive Graph Rewiring via the Lovász Bound | ✓ Link | 87.58% | | | | CT-Layer | 2022-06-15 |
| Learning metrics for persistence-based summaries and applications for graph classification | ✓ Link | 87.5% | | | | WKPI-kcenters | 2019-04-27 |
| Deep Graph Kernels | | 87.44% | | | | DGK | 2015-08-10 |
| Wasserstein Weisfeiler-Lehman Graph Kernels | ✓ Link | 87.27% | | | | WWL | 2019-06-04 |
| DAGCN: Dual Attention Graph Convolutional Networks | ✓ Link | 87.22% | | | | DAGCN | 2019-04-04 |
| Online Graph Dictionary Learning | ✓ Link | 87.09% | | | | GDL-g (SP) | 2021-02-12 |
| edGNN: a Simple and Powerful GNN for Directed Labeled Graphs | ✓ Link | 86.9% | | | | edGNN (avg) | 2019-04-18 |
| DiffWire: Inductive Graph Rewiring via the Lovász Bound | ✓ Link | 86.9% | | | | GAP-Layer (Rcut) | 2022-06-15 |
| DiffWire: Inductive Graph Rewiring via the Lovász Bound | ✓ Link | 86.9% | | | | GAP-Layer (Ncut) | 2022-06-15 |
| Capsule Graph Neural Network | ✓ Link | 86.67% | | | | CapsGNN | 2019-05-01 |
| Optimal Transport for structured data with application on graphs | ✓ Link | 86.42% | | | | FGW wl h=2 sp | 2018-05-23 |
| Rep the Set: Neural Networks for Learning Set Representations | ✓ Link | 86.33% | | | | ApproxRepSet | 2019-04-03 |
| Variational Recurrent Neural Networks for Graph Classification | ✓ Link | 86.3% | | | | VRGC | 2019-02-07 |
| Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks | ✓ Link | 86.1% | | | | k-GNN | 2018-10-04 |
| An End-to-End Deep Learning Architecture for Graph Classification | ✓ Link | 85.83% | | | | DGCNN | 2018-04-29 |
| PANDA: Expanded Width-Aware Message Passing Beyond Rewiring | ✓ Link | 85.75% | | | | GCN + PANDA | 2024-06-06 |
| Fast Graph Representation Learning with PyTorch Geometric | ✓ Link | 85.7% | | | | GIN-0 | 2019-03-06 |
| Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling | ✓ Link | 84.7% | | | | NDP | 2019-10-24 |
| Propagation kernels: efficient graph kernels from propagated information | ✓ Link | 84.5% | | | | Propagation kernels (pk) | 2019-02-01 |
| On Valid Optimal Assignment Kernels and Applications to Graph Classification | | 84.5% | | | | WL-OA | 2016-06-03 |
| SPI-GCN: A Simple Permutation-Invariant Graph Convolutional Network | | 84.40% | | | | SPI-GCN | 2019-04-08 |
| Accurate Learning of Graph Representations with Graph Multiset Pooling | ✓ Link | 83.44% | | | | GMT | 2021-02-23 |
| Function Space Pooling For Graph Convolutional Networks | | 83.3% | | | | Function Space Pooling | 2019-05-15 |
| IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification | ✓ Link | 83.3% | | | | Function Space Pooling | 2019-07-22 |
| Optimal Transport for structured data with application on graphs | ✓ Link | 83.26% | | | | FGW raw sp | 2018-05-23 |
| graph2vec: Learning Distributed Representations of Graphs | ✓ Link | 83.15% ± 9.25% | | | | graph2vec | 2017-07-17 |
| Graph Convolutional Networks with EigenPooling | ✓ Link | 79.5% | | | | EigenGCN-3 | 2019-04-30 |
| Online Graph Dictionary Learning | ✓ Link | 58.45% | | | | GDL-g (ADJ) | 2021-02-12 |
| A Persistent Weisfeiler–Lehman Procedure for Graph Classification | ✓ Link | | | 90.51 | | P-WL-C | 2019-06-09 |
| Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns | ✓ Link | | | | 86.14 | G-Tuning | 2023-12-21 |