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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Elborough, Lauren, Taylor, Duncan, Humphries, Melissa
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912047871033344
author Elborough, Lauren
Taylor, Duncan
Humphries, Melissa
author_facet Elborough, Lauren
Taylor, Duncan
Humphries, Melissa
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2409_18156
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A novel application of Shapley values for large multidimensional time-series data: Applying explainable AI to a DNA profile classification neural network
Elborough, Lauren
Taylor, Duncan
Humphries, Melissa
Quantitative Methods
Machine Learning
Genomics
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
title A novel application of Shapley values for large multidimensional time-series data: Applying explainable AI to a DNA profile classification neural network
topic Quantitative Methods
Machine Learning
Genomics
url https://arxiv.org/abs/2409.18156