Атрибуция признаков

AbstractFeature attribution a.k.a. input salience methods which assign an importance score to a feature are abundant but may produce surprisingly different results for the same model on the same input. …...

AbstractState-of-the-art approaches for hate-speech detection usually exhibit poor performance in out-of-domain settings. This occurs, typically, due to classifiers overemphasizing source-specific information that negatively impacts its domain invariance. Prior work has …...

AbstractWith the growing popularity of deep-learning models, model understanding becomes more important. Much effort has been devoted to demystify deep neural networks for better explainability. Some feature attribution methods have …...