Front-propagation Algorithm: Explainable AI Technique for Extracting Linear Function Approximations from Neural Networks

TL;DR

The paper presents the front-propagation algorithm, a real-time, explainable AI technique that extracts accurate linear explanations of neural network decisions in a single forward pass.

Contribution

It introduces a novel front-propagation algorithm that efficiently provides linear explanations of neural networks, enabling real-time interpretability.

Findings

Accurately extracts linear explanations in a single forward pass.

Operates in real-time, suitable for deployment.

Effective across multiple neural network architectures.

Abstract

This paper introduces the front-propagation algorithm, a novel eXplainable AI (XAI) technique designed to elucidate the decision-making logic of deep neural networks. Unlike other popular explainability algorithms such as Integrated Gradients or Shapley Values, the proposed algorithm is able to extract an accurate and consistent linear function explanation of the network in a single forward pass of the trained model. This nuance sets apart the time complexity of the front-propagation as it could be running real-time and in parallel with deployed models. We packaged this algorithm in a software called $\texttt{front-prop}$ and we demonstrate its efficacy in providing accurate linear functions with three different neural network architectures trained on publicly available benchmark datasets.