| Learning metrics for persistence-based summaries and applications for graph classification | ✓ Link | 87.3 | WKPI-kcenters | 2019-04-27 |
| On Valid Optimal Assignment Kernels and Applications to Graph Classification | | 86.3 | WL-OA | 2016-06-03 |
| An end-to-end attention-based approach for learning on graphs | ✓ Link | 84.976±0.551 | ESA (Edge set attention, no positional encodings) | 2024-02-16 |
| Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings | ✓ Link | 84.7 | δ-2-LWL | 2019-04-02 |
| CIN++: Enhancing Topological Message Passing | ✓ Link | 84.5 | CIN++ | 2023-06-06 |
| How Powerful are Graph Neural Networks? | ✓ Link | 84.155±0.812 | GIN | 2018-10-01 |
| Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes | | 84.0 | PIN | 2023-08-13 |
| DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks | ✓ Link | 83.961±1.141 | DropGIN | 2021-11-11 |
| A New Perspective on the Effects of Spectrum in Graph Neural Networks | ✓ Link | 83.62 | Spec-GN | 2021-12-14 |
| Cell Attention Networks | ✓ Link | 83.6 | CAN | 2022-09-16 |
| Propagation kernels: efficient graph kernels from propagated information | ✓ Link | 83.5 | Propagation kernels (pk) | 2019-02-01 |
| Principal Neighbourhood Aggregation for Graph Nets | ✓ Link | 83.382±1.045 | PNA | 2020-04-12 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 83.140±1.248 | GCN | 2016-09-09 |
| How Attentive are Graph Attention Networks? | ✓ Link | 83.092±0.764 | GATv2 | 2021-05-30 |
| Gaussian-Induced Convolution for Graphs | | 82.86 | GIC | 2018-11-11 |
| Graph Attention Networks | ✓ Link | 82.560±0.601 | GAT | 2017-10-30 |
| Provably Powerful Graph Networks | ✓ Link | 82.23 | PPGN | 2019-05-27 |
| Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs | ✓ Link | 82.14 | ECC (5 scores) | 2017-04-10 |
| Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules | ✓ Link | 82.0 | Multigraph ChebNet | 2018-11-23 |
| Recipe for a General, Powerful, Scalable Graph Transformer | ✓ Link | 81.256±0.501 | GraphGPS | 2022-05-25 |
| Hierarchical Graph Pooling with Structure Learning | ✓ Link | 80.67 | HGP-SL | 2019-11-14 |
| When Work Matters: Transforming Classical Network Structures to Graph CNN | | 80.66 | G_DenseNet | 2018-07-07 |
| Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck | ✓ Link | 77.54±1.51 | S-CGIB | 2025-02-20 |
| Graph isomorphism UNet | ✓ Link | 77 | GIUNet | 2023-08-23 |
| Relational Reasoning Over Spatial-Temporal Graphs for Video Summarization | | 75.85 | SAEPool_h | 2022-04-06 |
| Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity | ✓ Link | 75.45±1.26 | UGT | 2023-08-18 |
| Graph Convolutional Networks with EigenPooling | ✓ Link | 74.90 | EigenGCN-3 | 2019-04-30 |
| Do Transformers Really Perform Bad for Graph Representation? | ✓ Link | 74.879±1.183 | Graphormer | 2021-06-09 |
| Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity | ✓ Link | 74.48 | UGraphEmb-F | 2019-04-01 |
| graph2vec: Learning Distributed Representations of Graphs | ✓ Link | 74.26 | Graph2Vec | 2017-07-17 |
| Self-Attention Graph Pooling | ✓ Link | 74.06 | SAGPool_g | 2019-04-17 |
| Multi-hop Attention-based Graph Pooling: A Personalized PageRank Perspective | ✓ Link | 73.43% | MAGPool | 2024-03-04 |
| Pure Transformers are Powerful Graph Learners | ✓ Link | 72.077±1.883 | TokenGT | 2022-07-06 |
| Subgraph Networks with Application to Structural Feature Space Expansion | | 71.06 | Deep WL SGN(0,1,2) | 2019-03-21 |
| ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations | ✓ Link | 70.07 | ASAP | 2019-11-18 |
| Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity | ✓ Link | 69.17 | UGraphEmb | 2019-04-01 |
| Self-Attention Graph Pooling | ✓ Link | 67.86 | SAGPool_h | 2019-04-17 |
| Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations | | 58.04 | BC + Capsules | 2019-02-22 |