Search Results for author:
Found 2 papers, 0 papers with code
Structural Explanations for Graph Neural Networks using HSIC
More specifically, we extend the GraphLIME method for node explanation with a group lasso and a fused lasso-based node explanation method.
Computationally Efficient Wasserstein Loss for Structured Labels
The problem of estimating the probability distribution of labels has been widely studied as a label distribution learning (LDL) problem, whose applications include age estimation, emotion analysis, and semantic segmentation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
