Feature Extraction Functions for Neural Logic Rule Learning
This work addresses the need for rule-based explanations in neural networks, offering a flexible method for domain-specific applications, though it appears incremental in combining existing neural logic approaches.
The paper tackled the problem of integrating symbolic human knowledge as logic rules into neural networks for ante-hoc explainability, proposing feature extracting functions that modify input feature distributions without special mathematical encoding, and demonstrated performance on sentiment classification with comparisons to two baselines.
Combining symbolic human knowledge with neural networks provides a rule-based ante-hoc explanation of the output. In this paper, we propose feature extracting functions for integrating human knowledge abstracted as logic rules into the predictive behavior of a neural network. These functions are embodied as programming functions, which represent the applicable domain knowledge as a set of logical instructions and provide a modified distribution of independent features on input data. Unlike other existing neural logic approaches, the programmatic nature of these functions implies that they do not require any kind of special mathematical encoding, which makes our method very general and flexible in nature. We illustrate the performance of our approach for sentiment classification and compare our results to those obtained using two baselines.