paper-with-me

Graph Regression 벤치마크

Graph Regression on F2

9개 결과 · ⬇ CSV · JSON

R2

0.872 0.8768 0.8815 0.8862 0.891 2016-09 2026-11 GCN — 0.878 (2016-09-09) GAT — 0.886 (2017-10-30) GIN — 0.887 (2018-10-01) PNA — 0.891 (2020-04-12) GATv2 — 0.885 (2021-05-30) DropGIN — 0.886 (2021-11-11) TokenGT — 0.872 (2022-07-06) ESA (Edge set attention, no positional encodings) — 0.891 (2024-02-16) GCN — 0.878 (2016-09-09) GAT — 0.886 (2017-10-30) GIN — 0.887 (2018-10-01) PNA — 0.891 (2020-04-12)
RankModel R2RMSE PaperCodeYear
1 ESA (Edge set attention, no positional encodings) 0.891±0.0000.335±0.891 An end-to-end attention-based approach for learning on graphs davidbuterez/edge-set-attention 2024
2 PNA 0.891±0.0000.336±0.891 Principal Neighbourhood Aggregation for Graph Nets rusty1s/pytorch_geometric · dmlc/dgl · lukecavabarrett/pna · +5 2020
3 GIN 0.887±0.0000.342±0.887 How Powerful are Graph Neural Networks? dmlc/dgl · dmlc/dgl · weihua916/powerful-gnns · +16 2018
4 GAT 0.886±0.0000.343±0.886 Graph Attention Networks labmlai/annotated_deep_learning_paper_implementations · dmlc/dgl · dmlc/dgl · +90 2017
5 DropGIN 0.886±0.0000.343±0.886 DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks karolismart/dropgnn 2021
6 GATv2 0.885±0.0000.344±0.885 How Attentive are Graph Attention Networks? labmlai/annotated_deep_learning_paper_implementations · rusty1s/pytorch_geometric · dmlc/dgl · +5 2021
7 GCN 0.878±0.0000.355±0.878 Semi-Supervised Classification with Graph Convolutional Networks dmlc/dgl · dmlc/dgl · tkipf/gcn · +52 2016
8 TokenGT 0.872±0.0000.363±0.872 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