2 papers
eess.SP2025
Using Graph Convolutional Networks to Address fMRI Small Data Problems
Thomas Screven, Andras Necz, Jason Smucny +1
Although great advances in the analysis of neuroimaging data have been made, a major challenge is a lack of training data. This is less problematic in tasks such as diagnosis, wher…
cs.LG2024
CHAOSMINING: Benchmarking Post-Hoc Attribution with Sparse Informative Features in High Dimensions
Ge Shi, Fangyi Liu, Ziwen Kan +3
Post-hoc attribution is widely used to identify important model inputs, but evaluating whether these attributions identify truly informative features is difficult because real data…