Have We Learned to Explain? How Interpretability Methods Can Learn to Encode Predictions in their Interpretations

Neil Jethani, Mukund Sudarshan, Yindalon Aphinyanaphongs, Rajesh Ranganath

Research output: Contribution to journalConference articlepeer-review


While the need for interpretable machine learning has been established, many common approaches are slow, lack fidelity, or hard to evaluate. Amortized explanation methods reduce the cost of providing interpretations by learning a global selector model that returns feature importances for a single instance of data. The selector model is trained to optimize the fidelity of the interpretations, as evaluated by a predictor model for the target. Popular methods learn the selector and predictor model in concert, which we show allows predictions to be encoded within interpretations. We introduce EVAL-X as a method to quantitatively evaluate interpretations and REAL-X as an amortized explanation method, which learn a predictor model that approximates the true data generating distribution given any subset of the input. We show EVAL-X can detect when predictions are encoded in interpretations and show the advantages of REAL-X through quantitative and radiologist evaluation.

Original languageEnglish (US)
Pages (from-to)1459-1467
Number of pages9
JournalProceedings of Machine Learning Research
StatePublished - 2021
Event24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021 - Virtual, Online, United States
Duration: Apr 13 2021Apr 15 2021

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability


Dive into the research topics of 'Have We Learned to Explain? How Interpretability Methods Can Learn to Encode Predictions in their Interpretations'. Together they form a unique fingerprint.

Cite this