Understanding Interlocking Dynamics of Cooperative Rationalization
This addresses a fundamental flaw in interpretability methods for neural networks, though it is incremental as it builds on existing rationalization paradigms.
The paper tackles the problem of model interlocking in cooperative rationalization, where the predictor overfits to the generator's selections, leading to sub-optimal explanations; the proposed A2R framework significantly alleviates this issue and improves alignment with human judgments on synthetic and real datasets.
Selective rationalization explains the prediction of complex neural networks by finding a small subset of the input that is sufficient to predict the neural model output. The selection mechanism is commonly integrated into the model itself by specifying a two-component cascaded system consisting of a rationale generator, which makes a binary selection of the input features (which is the rationale), and a predictor, which predicts the output based only on the selected features. The components are trained jointly to optimize prediction performance. In this paper, we reveal a major problem with such cooperative rationalization paradigm -- model interlocking. Interlocking arises when the predictor overfits to the features selected by the generator thus reinforcing the generator's selection even if the selected rationales are sub-optimal. The fundamental cause of the interlocking problem is that the rationalization objective to be minimized is concave with respect to the generator's selection policy. We propose a new rationalization framework, called A2R, which introduces a third component into the architecture, a predictor driven by soft attention as opposed to selection. The generator now realizes both soft and hard attention over the features and these are fed into the two different predictors. While the generator still seeks to support the original predictor performance, it also minimizes a gap between the two predictors. As we will show theoretically, since the attention-based predictor exhibits a better convexity property, A2R can overcome the concavity barrier. Our experiments on two synthetic benchmarks and two real datasets demonstrate that A2R can significantly alleviate the interlock problem and find explanations that better align with human judgments. We release our code at https://github.com/Gorov/Understanding_Interlocking.