ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques

Junhao Liu, Xin Zhang

Primary Area: visualization or interpretation of learned representations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: machine learning, interpretability, temporal, local, model-agnostic

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose a framework, ReX, to make general local model-agnostic explanation techniques explain models processing variable-length data better.

Abstract: Advanced machine learning models that can handle inputs of variable lengths are powerful, but often hard to interpret. The lack of transparency hinders their adoption in many domains. Explanation techniques are essential for improving transparency. However, existing model-agnostic general explanation techniques do not consider the variable lengths of input data points, which limits their effectiveness. To address this limitation, we propose ReX, a general framework for adapting various explanation techniques to models that process variable-length inputs, expanding explanation coverage to data points of different lengths. Our approach adds temporal information to the explanations generated by existing techniques without altering their core algorithms. We instantiate our approach on three popular explanation techniques: Anchors, LIME, and Kernel SHAP. To evaluate the effectiveness of ReX, we apply our approach to five models in two different tasks. Our evaluation results demonstrate that our approach significantly improves the fidelity and understandability of explanations.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2333