Self-Interpretable Model with Transformation Equivariant InterpretationDownload PDF

Published: 09 Nov 2021, Last Modified: 05 May 2023NeurIPS 2021 PosterReaders: Everyone
Keywords: interpretable machine learning, transformation equivariance, computer vision
TL;DR: We propose a self-interpretable model that has transformation-equivariant interpretations, and comparable expressive power as benchmark black-box model.
Abstract: With the proliferation of machine learning applications in the real world, the demand for explaining machine learning predictions continues to grow especially in high-stakes fields. Recent studies have found that interpretation methods can be sensitive and unreliable, where the interpretations can be disturbed by perturbations or transformations of input data. To address this issue, we propose to learn robust interpretation through transformation equivariant regularization in a self-interpretable model. The resulting model is capable of capturing valid interpretation that is equivariant to geometric transformations. Moreover, since our model is self-interpretable, it enables faithful interpretations that reflect the true predictive mechanism. Unlike existing self-interpretable models, which usually sacrifice expressive power for the sake of interpretation quality, our model preserves the high expressive capability comparable to the state-of-the-art deep learning models in complex tasks, while providing visualizable and faithful high-quality interpretation. We compare with various related methods and validate the interpretation quality and consistency of our model.
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
Supplementary Material: pdf
18 Replies