| Universal Graph Transformer Self-Attention Networks | ✓ Link | 95.67% | U2GNN (Unsupervised) | 2019-09-26 |
| Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks | ✓ Link | 84.33% | MEWISPool | 2021-07-03 |
| An end-to-end attention-based approach for learning on graphs | ✓ Link | 83.529±1.743 | ESA (Edge set attention, no positional encodings) | 2024-02-16 |
| DDGK: Learning Graph Representations for Deep Divergence Graph Kernels | ✓ Link | 83.14% | DDGK | 2019-04-21 |
| Graph U-Nets | ✓ Link | 82.43% | Graph U-Nets | 2019-05-11 |
| Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning | ✓ Link | 82.40% | DUGNN | 2019-09-22 |
| Hierarchical Graph Representation Learning with Differentiable Pooling | ✓ Link | 82.07% | S2V (with 2 DiffPool) | 2018-06-22 |
| Learning metrics for persistence-based summaries and applications for graph classification | ✓ Link | 82.0% | WKPI-kmeans | 2019-04-27 |
| Graph Representation Learning via Hard and Channel-Wise Attention Networks | ✓ Link | 81.71% | hGANet | 2019-07-05 |
| Hierarchical Graph Pooling with Structure Learning | ✓ Link | 80.96% | HGP-SL | 2019-11-14 |
| Semi-Supervised Graph Classification: A Hierarchical Graph Perspective | ✓ Link | 80.88% | SEAL-SAGE | 2019-04-10 |
| Hierarchical Graph Representation Learning with Differentiable Pooling | ✓ Link | 80.64% | GNN (DiffPool) | 2018-06-22 |
| Relation order histograms as a network embedding tool | ✓ Link | 80.45% | NERO | 2021-06-09 |
| Universal Graph Transformer Self-Attention Networks | ✓ Link | 80.23% | U2GNN | 2019-09-26 |
| Multi-hop Attention-based Graph Pooling: A Personalized PageRank Perspective | ✓ Link | 79.83% | MAGPool | 2024-03-04 |
| Wasserstein Weisfeiler-Lehman Graph Kernels | ✓ Link | 79.69% | WWL | 2019-06-04 |
| Graph Star Net for Generalized Multi-Task Learning | ✓ Link | 79.60% | GraphStar | 2019-06-21 |
| An End-to-End Deep Learning Architecture for Graph Classification | ✓ Link | 79.37% | DGCNN | 2018-04-29 |
| Principal Neighbourhood Aggregation for Graph Nets | ✓ Link | 78.992±4.407 | PNA | 2020-04-12 |
| Propagation kernels: efficient graph kernels from propagated information | ✓ Link | 78.8% | Propagation kernels (pk) | 2019-02-01 |
| Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification | ✓ Link | 78.78% | GFN | 2019-05-11 |
| An End-to-End Deep Learning Architecture for Graph Classification | ✓ Link | 78.72% | DGCNN (sum) | 2018-04-29 |
| Accurate Learning of Graph Representations with Graph Multiset Pooling | ✓ Link | 78.72% | GMT | 2021-02-23 |
| Graph-level Representation Learning with Joint-Embedding Predictive Architectures | ✓ Link | 78.64% | Graph-JEPA | 2023-09-27 |
| Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification | ✓ Link | 78.62% | GFN-light | 2019-05-11 |
| Graph Convolutional Networks with EigenPooling | ✓ Link | 78.6% | EigenGCN-3 | 2019-04-30 |
| Wasserstein Embedding for Graph Learning | ✓ Link | 78.6% | WEGL | 2020-06-16 |
| Understanding Attention and Generalization in Graph Neural Networks | ✓ Link | 78.36% | Weak-supervised ChebyNet | 2019-05-08 |
| DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks | ✓ Link | 78.151±3.711 | DropGIN | 2021-11-11 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 78.151±3.465 | GCN | 2016-09-09 |
| Graph Capsule Convolutional Neural Networks | ✓ Link | 77.62% | GCAPS-CNN | 2018-05-21 |
| A simple yet effective baseline for non-attributed graph classification | ✓ Link | 77.5% | LDP + distance | 2018-11-08 |
| How Powerful are Graph Neural Networks? | ✓ Link | 77.311±2.223 | GIN | 2018-10-01 |
| DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model | | 77.21% | DGCNN | 2017-12-10 |
| ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations | ✓ Link | 76.87 | ASAP | 2019-11-18 |
| A Fair Comparison of Graph Neural Networks for Graph Classification | ✓ Link | 76.6% | DGCNN | 2019-12-20 |
| Self-Attention Graph Pooling | ✓ Link | 76.45% | SAGPool_h | 2019-04-17 |
| Learning Convolutional Neural Networks for Graphs | ✓ Link | 76.27% | PSCN | 2016-05-17 |
| TREE-G: Decision Trees Contesting Graph Neural Networks | ✓ Link | 76.2% | TREE-G | 2022-07-06 |
| Self-Attention Graph Pooling | ✓ Link | 76.19% | SAGPool_g | 2019-04-17 |
| A Non-Negative Factorization approach to node pooling in Graph Convolutional Neural Networks | | 76.0% | 1-NMFPool | 2019-09-07 |
| How Attentive are Graph Attention Networks? | ✓ Link | 75.966±2.191 | GATv2 | 2021-05-30 |
| A simple yet effective baseline for non-attributed graph classification | ✓ Link | 75.5% | LDP | 2018-11-08 |
| A Novel Higher-order Weisfeiler-Lehman Graph Convolution | ✓ Link | 75.4 | 2-WL-GNN | 2020-07-01 |
| Capsule Graph Neural Network | ✓ Link | 75.38% | CapsGNN | 2019-05-01 |
| Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations | | 74.86% | BC + Capsules | 2019-02-22 |
| Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs | ✓ Link | 74.1% | ECC (5 scores) | 2017-04-10 |
| Pure Transformers are Powerful Graph Learners | ✓ Link | 73.950±3.361 | TokenGT | 2022-07-06 |
| Deep Graph Kernels | | 73.50% | DGK | 2015-08-10 |
| Graph Attention Networks | ✓ Link | 73.109±3.413 | GAT | 2017-10-30 |
| Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling | ✓ Link | 72% | NDP | 2019-10-24 |
| Anonymous Walk Embeddings | ✓ Link | 71.51% | AWE | 2018-05-30 |
| A Simple Baseline Algorithm for Graph Classification | ✓ Link | 24.6% | SF + RFC | 2018-10-22 |