Invariant Rationalization


Published on


Selective rationalization improves neural network interpretability by identifying a small subset of input features {—} the rationale {—} that best explains or supports the prediction. A typical rationalization criterion, i.e. maximum mutual information (MMI), finds the rationale that maximizes the prediction performance based only on the rationale. However, MMI can be problematic because it picks up spurious correlations between the input features and the output. Instead, we introduce a game-theoretic invariant rationalization criterion where the rationales are constrained to enable the same predictor to be optimal across different environments. We show both theoretically and empirically that the proposed rationales can rule out spurious correlations and generalize better to different test scenarios. The resulting explanations also align better with human judgments.

Please cite our work using the BibTeX below.

  title = 	 {Invariant Rationalization},
  author =       {Chang, Shiyu and Zhang, Yang and Yu, Mo and Jaakkola, Tommi},
  booktitle = 	 {Proceedings of the 37th International Conference on Machine Learning},
  pages = 	 {1448--1458},
  year = 	 {2020},
  editor = 	 {III, Hal Daumé and Singh, Aarti},
  volume = 	 {119},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {13--18 Jul},
  publisher =    {PMLR},
  pdf = 	 {},
  url = 	 {}
Close Modal