Invariant Rationalization
This work addresses interpretability issues in neural networks for researchers and practitioners by reducing reliance on spurious features, though it is incremental as it builds on existing rationalization methods.
The paper tackles the problem of spurious correlations in selective rationalization by introducing an invariant rationalization criterion based on game theory, which improves generalization across environments and better aligns with human judgments.
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, generalize better to different test scenarios, and align better with human judgments. Our data and code are available.