A novel application of Shapley values for large multidimensional time-series data: Applying explainable AI to a DNA profile classification neural network

TL;DR

This paper introduces an efficient method for applying Shapley values to large, high-dimensional time-series data, demonstrated on DNA profile classification with neural networks, enabling explainable AI in forensic applications.

Contribution

It adapts superpixel concepts to time-series data for scalable Shapley value computation, facilitating explainability in complex neural network classifications.

Findings

Method enables fast Shapley value computation for 31,200-point DNA profiles.

Application achieves accurate, interpretable classifications in forensic DNA analysis.

Demonstrates potential for explainable AI in high-dimensional, real-world data.

Abstract

The application of Shapley values to high-dimensional, time-series-like data is computationally challenging - and sometimes impossible. For $N$ inputs the problem is $2^N$ hard. In image processing, clusters of pixels, referred to as superpixels, are used to streamline computations. This research presents an efficient solution for time-seres-like data that adapts the idea of superpixels for Shapley value computation. Motivated by a forensic DNA classification example, the method is applied to multivariate time-series-like data whose features have been classified by a convolutional neural network (CNN). In DNA processing, it is important to identify alleles from the background noise created by DNA extraction and processing. A single DNA profile has $31,200$ scan points to classify, and the classification decisions must be defensible in a court of law. This means that classification is routinely performed by human readers - a monumental and time consuming process. The application of a CNN with fast computation of meaningful Shapley values provides a potential alternative to the classification. This research demonstrates the realistic, accurate and fast computation of Shapley values for this massive task