Citation network of scientific papers. 2708 nodes, 5429 edges, 7 classes. Classic GNN benchmark.
6 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.
| # | Model | Org | Submitted | Paper / code | accuracy |
|---|---|---|---|---|---|
| 01 | ACNet | — | Apr 2019 | Adaptively Connected Neural Networks · code | 83.50 |
| 02 | LGCN | — | Aug 2018 | Large-Scale Learnable Graph Convolutional Networks · code | 83.30 |
| 03 | GAT | — | Oct 2017 | Graph Attention Networks · code | 83 |
| 04 | MoNet | — | Nov 2016 | Geometric deep learning on graphs and manifolds using mi… · code | 81.70 |
| 05 | Planetoid* | — | Mar 2016 | Revisiting Semi-Supervised Learning with Graph Embedding… · code | 75.70 |
| 06 | DeepWalk | — | Mar 2014 | DeepWalk: Online Learning of Social Representations · code | 67.20 |
Each row below marks a model that broke the previous record on accuracy. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.
Higher scores win. Each subsequent entry improved upon the previous best.
Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.
Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.