paper-with-me

Graph Regression 벤치마크

Graph Regression on KIT

9개 결과 · ⬇ CSV · JSON

R2

0.8 0.8108 0.8215 0.8322 0.843 2016-09 2026-11 GCN — 0.814 (2016-09-09) GAT — 0.833 (2017-10-30) GIN — 0.833 (2018-10-01) PNA — 0.843 (2020-04-12) GATv2 — 0.826 (2021-05-30) GINDrop — 0.835 (2021-11-11) TokenGT — 0.8 (2022-07-06) ESA (Edge set attention, no positional encodings) — 0.841 (2024-02-16) GCN — 0.814 (2016-09-09) GAT — 0.833 (2017-10-30) PNA — 0.843 (2020-04-12)
RankModel R2RMSE PaperCodeYear
1 PNA 0.843±0.0000.430±0.843 Principal Neighbourhood Aggregation for Graph Nets rusty1s/pytorch_geometric · dmlc/dgl · lukecavabarrett/pna · +5 2020
2 ESA (Edge set attention, no positional encodings) 0.841±0.0000.433±0.841 An end-to-end attention-based approach for learning on graphs davidbuterez/edge-set-attention 2024
3 GINDrop 0.835±0.0000.441±0.835 DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks karolismart/dropgnn 2021
4 GAT 0.833±0.0000.443±0.833 Graph Attention Networks labmlai/annotated_deep_learning_paper_implementations · dmlc/dgl · dmlc/dgl · +90 2017
5 GIN 0.833±0.0000.444±0.833 How Powerful are Graph Neural Networks? dmlc/dgl · dmlc/dgl · weihua916/powerful-gnns · +16 2018
6 GATv2 0.826±0.0000.453±0.826 How Attentive are Graph Attention Networks? labmlai/annotated_deep_learning_paper_implementations · rusty1s/pytorch_geometric · dmlc/dgl · +5 2021
7 GCN 0.814±0.0000.469±0.814 Semi-Supervised Classification with Graph Convolutional Networks dmlc/dgl · dmlc/dgl · tkipf/gcn · +52 2016
8 TokenGT 0.800±0.0000.486±0.800 Pure Transformers are Powerful Graph Learners jw9730/tokengt · luis-mueller/wl-transformers 2022
9 Graphormer OOMOOM Do Transformers Really Perform Bad for Graph Representation? microsoft/Graphormer · Microsoft/Graphormer · dpstart/graphormer_new · +2 2021
1–9 / 9 페이지당 10 20 50 100