Learning to Explain: An Information-Theoretic Perspective on Model Interpretation

By Jianbo Chen, Le Song, Martin J. Wainwright, Michael I. Jordan. 2018

666 citations recorded by the source corpus.

We introduce instancewise feature selection as a methodology for model interpretation. Our method is based on learning a function to extract a subset of features that are most informative for each given example. This feature selector is trained to maximize the mutual information between selected features and the response variable, where the conditional distribution of the response variable given the input is the model to be explained. We develop an efficient variational approximation to the mutual information, and show the effectiveness of our method on a variety of synthetic and real data sets using both quantitative metrics and human evaluation.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Information Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Yoshua Bengio
  3. Percy Liang
  4. Jianfeng Gao
  5. Sergey Levine
  6. Noah A. Smith
  7. Ruslan Salakhutdinov
  8. Luke S. Zettlemoyer

In Safety, Robustness & Interpretability

  1. Riccardo Guidotti
  2. Tomas Pfister
  3. Sercan Ö. Arik
  4. Dino Pedreschi
  5. Yoav Goldberg
  6. Tommi S. Jaakkola
  7. Su-In Lee
  8. Alon Jacovi

In Information Theory

  1. Stefano Ermon
  2. Walter Karlen
  3. Patrick Schwab
  4. Tomas Pfister
  5. Yoav Goldberg
  6. Sercan Ö. Arik
  7. Alon Jacovi
  8. Sang Michael Xie

Citations in the corpus