LIPEx-Locally Interpretable Probabilistic Explanations-To Look Beyond The True Class
Hongbo Zhu, Angelo Cangelosi, Procheta Sen, Anirbit Mukherjee

TL;DR
LIPEx is a novel perturbation-based explanation method that accurately replicates model probabilities and reveals feature effects on predictions, outperforming existing methods in data efficiency and explanation quality.
Contribution
This paper introduces LIPEx, a new framework for local probabilistic explanations that improves upon LIME in accuracy and efficiency by using a matrix regression approach based on the Hellinger distance.
Findings
LIPEx replicates model probability distributions more accurately.
LIPEx provides detailed feature impact on class probabilities.
LIPEx is approximately 53% faster than LIME in explanation computation.
Abstract
In this work, we instantiate a novel perturbation-based multi-class explanation framework, LIPEx (Locally Interpretable Probabilistic Explanation). We demonstrate that LIPEx not only locally replicates the probability distributions output by the widely used complex classification models but also provides insight into how every feature deemed to be important affects the prediction probability for each of the possible classes. We achieve this by defining the explanation as a matrix obtained via regression with respect to the Hellinger distance in the space of probability distributions. Ablation tests on text and image data, show that LIPEx-guided removal of important features from the data causes more change in predictions for the underlying model than similar tests based on other saliency-based or feature importance-based Explainable AI (XAI) methods. It is also shown that compared to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExplainable Artificial Intelligence (XAI) · Adversarial Robustness in Machine Learning · Anomaly Detection Techniques and Applications
MethodsLocal Interpretable Model-Agnostic Explanations
