A cognitive diagnostic framework for evaluating machine learning model multi-faced Ability
We test our diagnoser on four public datasets: Titanic, CIFAR-100, ESOL and Diamond.
The results of our paper can be reproduced by simply running the following command:
./multiple_run.sh
The training code of learners in each dataset can be found here: https://github.com/KellyGong/Camilla-Learner-Training