paper-with-me

Graph Classification 벤치마크

Graph Classification on MalNet-Tiny

8개 결과 · ⬇ CSV · JSON

Accuracy

93.36 93.72 94.08 94.44 94.8 2022-05 2026-09 GPS — 93.36 (2022-05-25) GPS — 93.36 (2022-05-25) Exphormer — 94.02 (2023-03-10) Exphormer — 94.02 (2023-03-10) ESA (Edge set attention, no positional encodings) — 94.8 (2024-02-16) ESA (Edge set attention, no positional encodings) — 94.8 (2024-02-16) GatedGCN+ — 94.6 (2025-02-13) GatedGCN+ — 94.6 (2025-02-13) GPS — 93.36 (2022-05-25) Exphormer — 94.02 (2023-03-10) ESA (Edge set attention, no positional encodings) — 94.8 (2024-02-16)
RankModel AccuracyMCC PaperCodeYear
1 ESA (Edge set attention, no positional encodings) 94.800±0.4240.935±0.005 An end-to-end attention-based approach for learning on graphs davidbuterez/edge-set-attention 2024
2 GatedGCN+ 94.600±0.570– Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence LUOyk1999/GNNPlus 2025
3 Exphormer 94.02±0.209– Exphormer: Sparse Transformers for Graphs hamed1375/exphormer 2023
4 GPS 93.36 ± 0.6– Recipe for a General, Powerful, Scalable Graph Transformer rampasek/GraphGPS · hamed1375/exphormer · graphcore/ogb-lsc-pcqm4mv2 · +1 2022
5 ESA (Edge set attention, no positional encodings) 94.800±0.4240.935±0.005 An end-to-end attention-based approach for learning on graphs davidbuterez/edge-set-attention 2024
6 GatedGCN+ 94.600±0.570– Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence LUOyk1999/GNNPlus 2025
7 Exphormer 94.02±0.209– Exphormer: Sparse Transformers for Graphs hamed1375/exphormer 2023
8 GPS 93.36 ± 0.6– Recipe for a General, Powerful, Scalable Graph Transformer rampasek/GraphGPS · hamed1375/exphormer · graphcore/ogb-lsc-pcqm4mv2 · +1 2022
1–8 / 8 페이지당 10 20 50 100