Backpropagation-based explainability method for unsupervised anomaly detection models based on autoencoder architectures

Abstract

The present invention relates to machine learning (ML) explainability (MLX). Herein are techniques for a novel relevance propagation rule in layer-wise relevance propagation (LRP) for feature attribution-based explanation (ABX) for a reconstructive autoencoder. In an embodiment, a reconstruction layer of a reconstructive neural network in a computer generates a reconstructed tuple that is based on an original tuple that contains many features. A reconstruction residual cost function calculates a reconstruction error that measures a difference between the original tuple and the reconstructed tuple. Applied to the reconstruction error is a novel reconstruction relevance propagation rule that assigns a respective reconstruction relevance to each reconstruction neuron in the reconstruction layer. Based on the reconstruction relevance of the reconstruction neurons, a respective feature relevance of each feature is determined, from which an ABX explanation may be automatically generated.