paper-with-me

Graph Classification 벤치마크

Graph Classification on NEURON-MULTI

10개 결과 · ⬇ CSV · JSON

Accuracy

44.3 50.5 56.7 62.9 69.1 2015-07 2026-09 PI-PL — 44.3 (2015-07-22) PI-PL — 44.3 (2015-07-22) SW — 57.3 (2017-06-11) SW — 57.3 (2017-06-11) PWGK — 45.5 (2017-06-12) PWGK — 45.5 (2017-06-12) WKPI-kcenters — 69.1 (2019-04-27) WKPI-kmeans — 56.2 (2019-04-27) WKPI-kcenters — 69.1 (2019-04-27) WKPI-kmeans — 56.2 (2019-04-27) PI-PL — 44.3 (2015-07-22) SW — 57.3 (2017-06-11) WKPI-kcenters — 69.1 (2019-04-27)
RankModel Accuracy PaperCodeYear
1 WKPI-kcenters 69.1 Learning metrics for persistence-based summaries and applications for graph classification topology474/WKPI 2019
2 SW 57.3 Sliced Wasserstein Kernel for Persistence Diagrams 2017
3 WKPI-kmeans 56.2 Learning metrics for persistence-based summaries and applications for graph classification topology474/WKPI 2019
4 PWGK 45.5 Kernel method for persistence diagrams via kernel embedding and weight factor genki-kusano/python-pwgk 2017
5 PI-PL 44.3 Persistence Images: A Stable Vector Representation of Persistent Homology scikit-tda/persim · MathieuCarriere/perslay · CSU-TDA/PersistenceImages · +1 2015
6 WKPI-kcenters 69.1 Learning metrics for persistence-based summaries and applications for graph classification topology474/WKPI 2019
7 SW 57.3 Sliced Wasserstein Kernel for Persistence Diagrams 2017
8 WKPI-kmeans 56.2 Learning metrics for persistence-based summaries and applications for graph classification topology474/WKPI 2019
9 PWGK 45.5 Kernel method for persistence diagrams via kernel embedding and weight factor genki-kusano/python-pwgk 2017
10 PI-PL 44.3 Persistence Images: A Stable Vector Representation of Persistent Homology scikit-tda/persim · MathieuCarriere/perslay · CSU-TDA/PersistenceImages · +1 2015
1–10 / 10 페이지당 10 20 50 100