State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions

TL;DR

This paper introduces state-regularized RNNs that improve interpretability, automata extraction, and long-term sequence modeling by incorporating a stochastic state transition mechanism, addressing key limitations of traditional RNNs.

Contribution

The paper proposes a novel state-regularization technique for RNNs that enhances interpretability and automata extraction while improving performance on long-term sequence tasks.

Findings

Easier extraction of finite state automata from RNNs.

RNNs operate more like automata with external memory.

Improved interpretability and explainability of RNN predictions.

Abstract

Recurrent neural networks are a widely used class of neural architectures. They have, however, two shortcomings. First, they are often treated as black-box models and as such it is difficult to understand what exactly they learn as well as how they arrive at a particular prediction. Second, they tend to work poorly on sequences requiring long-term memorization, despite having this capacity in principle. We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications. This mechanism, which we term state-regularization, makes RNNs transition between a finite set of learnable states. We evaluate state-regularized RNNs on (1) regular languages for the purpose of automata extraction; (2) non-regular languages such as balanced parentheses and palindromes where external memory is required; and (3) real-word sequence learning tasks for sentiment analysis, visual object recognition and text categorisation. We show that state-regularization (a) simplifies the extraction of finite state automata that display an RNN's state transition dynamic; (b) forces RNNs to operate more like automata with external memory and less like finite state machines, which potentiality leads to a more structural memory; (c) leads to better interpretability and explainability of RNNs by leveraging the probabilistic finite state transition mechanism over time steps.