Understanding Interlocking Dynamics of Cooperative Rationalization

Understand

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.