| An end-to-end attention-based approach for learning on graphs | ✓ Link | 0.595±0.013 | 0.977±0.001 | ESA (Edge set attention, no positional encodings) | 2024-02-16 |
| DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks | ✓ Link | 0.657±0.059 | 0.972±0.005 | DropGIN | 2021-11-11 |
| How Attentive are Graph Attention Networks? | ✓ Link | 0.676±0.081 | 0.970±0.007 | GATv2 | 2021-05-30 |
| How Powerful are Graph Neural Networks? | ✓ Link | 0.744±0.083 | 0.964±0.008 | GIN | 2018-10-01 |
| Graph Attention Networks | ✓ Link | 0.791±0.101 | 0.959±0.011 | GAT | 2017-10-30 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 0.815±0.086 | 0.957±0.009 | GCN | 2016-09-09 |
| Principal Neighbourhood Aggregation for Graph Nets | ✓ Link | 0.870±0.081 | 0.951±0.009 | PNA | 2020-04-12 |
| Pure Transformers are Powerful Graph Learners | ✓ Link | 1.038±0.125 | 0.930±0.018 | TokenGT | 2022-07-06 |
| Do Transformers Really Perform Bad for Graph Representation? | ✓ Link | 1.065±0.039 | 0.927±0.005 | Graphormer | 2021-06-09 |
| Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning | ✓ Link | 1.09 | | SMA | 2024-02-22 |
| A Bayesian Flow Network Framework for Chemistry Tasks | ✓ Link | 1.418 | | ChemBFN | 2024-07-28 |
| Recipe for a General, Powerful, Scalable Graph Transformer | ✓ Link | 1.462±0.188 | 0.861±0.037 | GraphGPS | 2022-05-25 |
| Uni-Mol: A Universal 3D Molecular Representation Learning Framework | ✓ Link | 1.620 | | Uni-Mol | 2022-09-08 |
| Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck | ✓ Link | 1.648±0.074 | | S-CGIB | 2025-02-20 |
| Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model | ✓ Link | 1.859 | | SPMM | 2022-11-19 |
| ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction | | 1.877 | | ChemRL-GEM | 2021-06-11 |
| Analyzing Learned Molecular Representations for Property Prediction | ✓ Link | 2.082 | | D-MPNN | 2019-04-02 |
| Self-Supervised Graph Transformer on Large-Scale Molecular Data | ✓ Link | 2.176 | | GROVER (base) | 2020-06-18 |
| Self-Supervised Graph Transformer on Large-Scale Molecular Data | ✓ Link | 2.272 | | GROVER (large) | 2020-06-18 |
| N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules | ✓ Link | 2.688 | | N-GramRF | 2018-06-24 |
| Strategies for Pre-training Graph Neural Networks | ✓ Link | 2.764 | | PretrainGNN | 2019-05-29 |
| N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules | ✓ Link | 5.061 | | N-GramXGB | 2018-06-24 |