What was the context? Wha was studied already?
Pre-trained deep learning models in a wide range of tasks usually have a complex model designs. This raises important questions about whether a deep model is ethical, trustworthy, or capable of performing as intended under various conditions.
Works on post-hoc explanations for black-box models, that have already been trained, do not change the model and hence preserve the predictive performance while providing the additional benefit of explainability. However, they have an high computational cost and may induce to trust issues.
Self-explaining models naturally solve these issues, making them an ideal choice when interpretability. These models can predict and explain simultaneously with a single forward propagation without any approximations or heuristic assumptions that decrease the faithfulness of explanations.
What was the objective? How was the data collected?
This paper proposes SELOR, a framework for upgrading a deep model with a Self-Explainable version with LOgic rule Reasoning capability. Their is inspired by neuro-symbolic reasoning, which integrates deep learning with logic rule reasoning to inherit advantages from both.
The main ideia behind the SELOR model was to separate the model into two partes as we can see on the image bellow:
First, the Prediction layer was replaced by an Antecedent generator. The goal is to map the latent representation of input into an explanation, instead of directly mapping to a prediction.
