Shapley-Study
Shapley-Study copied to clipboard
AI-secure
[CVPR 2021] Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
I'm currently using LightGBM as the model for iterations of TMCShapley. LightGBM supports 'continued training with input scores', do you think it would be possible to tweak the implementation to...
I'm now having some promising results with TMCShapley and KNNShapley. Thanks a lot for the good work. I'm looking for results that translate into incorrect label discovery and deep NN...
Very impressed by this piece of work. Has any thought gone into how the KNN Shapley approach could be adapted to the multi-label case while retaining its efficiency? For that...