paper-with-me

Formation Energy 벤치마크

Formation Energy on OQM9HK

8개 결과 · ⬇ CSV · JSON

MAE 낮을수록 좋음

0.03433 0.1032 0.1722 0.2411 0.31 2017-06 2026-09 SchNet — 0.31 (2017-06-26) SchNet — 0.31 (2017-06-26) CGNN Full Ensemble — 0.03433 (2022-09-30) CGNN Trio Ensemble — 0.03658 (2022-09-30) CGNN — 0.04249 (2022-09-30) CGNN Full Ensemble — 0.03433 (2022-09-30) CGNN Trio Ensemble — 0.03658 (2022-09-30) CGNN — 0.04249 (2022-09-30) SchNet — 0.31 (2017-06-26) CGNN Full Ensemble — 0.03433 (2022-09-30)
RankModel MAE PaperCodeYear
1 CGNN Full Ensemble 0.03433 OQM9HK: A Large-Scale Graph Dataset for Machine Learning in Materials Science Tony-Y/cgnn 2022
2 CGNN Trio Ensemble 0.03658 OQM9HK: A Large-Scale Graph Dataset for Machine Learning in Materials Science Tony-Y/cgnn 2022
3 CGNN 0.04249 ± 0.00037 OQM9HK: A Large-Scale Graph Dataset for Machine Learning in Materials Science Tony-Y/cgnn 2022
4 SchNet 0.31 SchNet: A continuous-filter convolutional neural network for modeling quantum interactions atomistic-machine-learning/schnetpack · atomistic-machine-learning/SchNet · xiuyu0000/new_papers_codes · +2 2017
5 CGNN Full Ensemble 0.03433 OQM9HK: A Large-Scale Graph Dataset for Machine Learning in Materials Science Tony-Y/cgnn 2022
6 CGNN Trio Ensemble 0.03658 OQM9HK: A Large-Scale Graph Dataset for Machine Learning in Materials Science Tony-Y/cgnn 2022
7 CGNN 0.04249 ± 0.00037 OQM9HK: A Large-Scale Graph Dataset for Machine Learning in Materials Science Tony-Y/cgnn 2022
8 SchNet 0.31 SchNet: A continuous-filter convolutional neural network for modeling quantum interactions atomistic-machine-learning/schnetpack · atomistic-machine-learning/SchNet · xiuyu0000/new_papers_codes · +2 2017
1–8 / 8 페이지당 10 20 50 100