A Functional Information Perspective on Model Interpretation

Itai Gat, Nitay Calderon, Roi Reichart, Tamir Hazan
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:7266-7278, 2022.

Abstract

Contemporary predictive models are hard to interpret as their deep nets exploit numerous complex relations between input elements. This work suggests a theoretical framework for model interpretability by measuring the contribution of relevant features to the functional entropy of the network with respect to the input. We rely on the log-Sobolev inequality that bounds the functional entropy by the functional Fisher information with respect to the covariance of the data. This provides a principled way to measure the amount of information contribution of a subset of features to the decision function. Through extensive experiments, we show that our method surpasses existing interpretability sampling-based methods on various data signals such as image, text, and audio.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-gat22a, title = {A Functional Information Perspective on Model Interpretation}, author = {Gat, Itai and Calderon, Nitay and Reichart, Roi and Hazan, Tamir}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {7266--7278}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/gat22a/gat22a.pdf}, url = {https://proceedings.mlr.press/v162/gat22a.html}, abstract = {Contemporary predictive models are hard to interpret as their deep nets exploit numerous complex relations between input elements. This work suggests a theoretical framework for model interpretability by measuring the contribution of relevant features to the functional entropy of the network with respect to the input. We rely on the log-Sobolev inequality that bounds the functional entropy by the functional Fisher information with respect to the covariance of the data. This provides a principled way to measure the amount of information contribution of a subset of features to the decision function. Through extensive experiments, we show that our method surpasses existing interpretability sampling-based methods on various data signals such as image, text, and audio.} }
Endnote
%0 Conference Paper %T A Functional Information Perspective on Model Interpretation %A Itai Gat %A Nitay Calderon %A Roi Reichart %A Tamir Hazan %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-gat22a %I PMLR %P 7266--7278 %U https://proceedings.mlr.press/v162/gat22a.html %V 162 %X Contemporary predictive models are hard to interpret as their deep nets exploit numerous complex relations between input elements. This work suggests a theoretical framework for model interpretability by measuring the contribution of relevant features to the functional entropy of the network with respect to the input. We rely on the log-Sobolev inequality that bounds the functional entropy by the functional Fisher information with respect to the covariance of the data. This provides a principled way to measure the amount of information contribution of a subset of features to the decision function. Through extensive experiments, we show that our method surpasses existing interpretability sampling-based methods on various data signals such as image, text, and audio.
APA
Gat, I., Calderon, N., Reichart, R. & Hazan, T.. (2022). A Functional Information Perspective on Model Interpretation. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:7266-7278 Available from https://proceedings.mlr.press/v162/gat22a.html.

Related Material