Path-Weighted Integrated Gradients for Interpretable Dementia Classification
This work addresses interpretability challenges in AI for medical diagnosis, specifically dementia classification, but is incremental as it builds upon existing Integrated Gradients.
The paper tackled the problem of improving attribution methods in explainable AI by introducing Path-Weighted Integrated Gradients (PWIG), a generalization of Integrated Gradients that uses a weighting function to enhance interpretability and reduce noise, with experiments on dementia classification showing it highlights clinically relevant brain regions.
Integrated Gradients (IG) is a widely used attribution method in explainable artificial intelligence (XAI). In this paper, we introduce Path-Weighted Integrated Gradients (PWIG), a generalization of IG that incorporates a customizable weighting function into the attribution integral. This modification allows for targeted emphasis along different segments of the path between a baseline and the input, enabling improved interpretability, noise mitigation, and the detection of path-dependent feature relevance. We establish its theoretical properties and illustrate its utility through experiments on a dementia classification task using the OASIS-1 MRI dataset. Attribution maps generated by PWIG highlight clinically meaningful brain regions associated with various stages of dementia, providing users with sharp and stable explanations. The results suggest that PWIG offers a flexible and theoretically grounded approach for enhancing attribution quality in complex predictive models.