Causality Causality Workbench                                                             Challenges in Machine Learning Causality

Unsupervised and Transfer Learning Challenge

Results

Phase 1

Global Rank Team name Experiment Validation global score Final global score
A H R S T A H R S T
1 AIO AIO 0.174359  0.863984  0.309499  0.640926  0.819456  0.218265  (1) 0.70433  (6) 0.495093  (1) 0.456918  (6) 0.846478  (1)
2 1055A exp1 0.138572  0.90853  0.373677  0.71457  0.817631  0.19061  (6) 0.735657  (3) 0.478162  (5) 0.58279  (1) 0.843724  (2)
3 Airbus A3XX 0.159464  0.852811  0.382997  0.675098  0.800615  0.217428  (2) 0.754497  (2) 0.472407  (7) 0.494932  (4) 0.839038  (3)
4 LISA LISA 0.193229  0.899473  0.323347  0.85109  0.810315  0.196023  (5) 0.806196  (1) 0.473066  (6) 0.476341  (5) 0.795915  (6)
5 NG-A3 Exp1TL 0.149326  0.794511  0.284878  0.606385  0.780955  0.182106  (9) 0.709893  (5) 0.489439  (2) 0.44926  (7) 0.808953  (5)
6 DM result 0.14958  0.762235  0.288033  0.505342  0.766101  0.205576  (3) 0.645239  (7) 0.484406  (4) 0.36892  (9) 0.793176  (7)
7 tkgw hiden 0.199477  0.839381  0.282352  0.581364  0.575429  0.199068  (4) 0.72103  (4) 0.401273  (12) 0.566349  (2) 0.619048  (11)
8 unpi FinMix 0.149895  0.791937  0.24402  0.520247  0.74397  0.185077  (7) 0.554518  (10) 0.412991  (9) 0.511921  (3) 0.779942  (8)
9 Datam1n md 0.145176  0.427362  0.302322  0.231921  0.787921  0.179791  (10) 0.521381  (11) 0.484514  (3) 0.33285  (11) 0.813034  (4)
10 KUNLP phase1 0.117479  0.52415  0.28887  0.424845  0.545683  0.097725  (14) 0.357168  (13) 0.407049  (10) 0.402064  (8) 0.645952  (10)
11 fallstone fallstone01 0.121899  0.489524  0.240936  0.210359  0.511008  0.18487  (8) 0.378116  (12) 0.406288  (11) 0.308947  (12) 0.550378  (13)
12 UCIrvine ps122 0.0435815  0.672252  0.224802  0.181759  0.643647  0.0297987  (15) 0.560286  (9) 0.393731  (13) 0.288652  (14) 0.65254  (9)
12 SKEL Exp160 0.00116856  0.672931    0.00749017  0.512821  0.00457078  (16) 0.630683  (8) 0.413343  (8) 0.0057408  (16) 0.559983  (12)
13 LvdM GaussianRBM 0.116615  0.615438  0.204486  0.266546  0.592335  0.169734  (11) 0.149608  (15) 0.381305  (14) 0.341783  (10) 0.0484396  (16)
14 sal a 0.111516  0.237371  0.194703  0.201955  0.281464  0.144041  (12) 0.330043  (14) 0.336936  (15) 0.303556  (13) 0.316896  (14)
15 RFFI-team 10000ex100tr10000h 0.108554  0.143108  0.0545443  0.169338  0.241784  0.113985  (13) 0.0768794  (16) 0.282305  (16) 0.273654  (15) 0.256059  (15)

Phase 2

Global Rank Team name Experiment Validation global score Final global score
A H R S T A H R S T
1 LISA agartha 0.192108  0.910381  0.301271  0.623844  0.816752  0.227307  (1) 0.861933  (1) 0.502948  (1) 0.565043  (3) 0.816009  (2)
2 tkgw crush 0.16017  0.844359  0.281741  0.884973  0.778118  0.197261  (2) 0.7533  (2) 0.40947  (4) 0.593283  (1) 0.811784  (3)
3 1055A phase2exp1 0.166751  0.906208  0.369143  0.756142  0.817631  0.151111  (4) 0.738125  (3) 0.499217  (2) 0.587319  (2) 0.843724  (1)
4 FAST teaf 0.142912  0.438727  0.198825  0.236124  0.580262  0.190855  (3) 0.357953  (4) 0.427478  (3) 0.33789  (5) 0.648536  (4)
5 RFFI-team t100hmod10000i1 0.113463  0.233021  0.21627  0.429057  0.359677  0.12849  (5) 0.0970518  (5) 0.336831  (6) 0.431914  (4) 0.513854  (6)
6 NG-A3 transfer7 0.117747  0.221498  0.259007  0.606771  0.739909  0.112783  (6) 0.0950054  (6) 0.363303  (5) 0.126217  (6) 0.566029  (5)

* The organizers detected that the team 1055A submitted by error their results on the validation set instead of those on the final evaluation set for the dataset Sylvester. The team was allowed to re-submit their results on that dataset and those are shown in the table. Without this correction, the 1055A team ranks 3rd and this is the official ranking (with the correction they rank 2nd ex aequo with tkgw).

** Due to an accidental release of the results on the final evaluation set on the scheduled deadline of phase 2, the planned grace period was canceled. However, the participants were permitted to make one last submission, follow this link to see the result table obtained with these additional submissions.