Document Type
Article
Rights
Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence
Disciplines
Computer Sciences
Abstract
Trust and credibility in machine learning models are bolstered by the ability of a model to explain its decisions. While explainability of deep learning models is a well-known challenge, a further challenge is clarity of the explanation itself for relevant stakeholders of the model. Layer-wise Relevance Propagation (LRP), an established explainability technique developed for deep models in computer vision, provides intuitive human-readable heat maps of input images. We present the novel application of LRP with tabular datasets containing mixed data (categorical and numerical) using a deep neural network (1D-CNN), for Credit Card Fraud detection and Telecom Customer Churn prediction use cases. We show how LRP is more effective than traditional explainability concepts of Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP) for explainability. This effectiveness is both local to a sample level and holistic over the whole testing set. We also discuss the significant computational time advantage of LRP (1–2 s) over LIME (22 s) and SHAP (108 s) on the same laptop, and thus its potential for real time application scenarios. In addition, our validation of LRP has highlighted features for enhancing model performance, thus opening up a new area of research of using XAI as an approach for feature subset selection.
DOI
https://doi.org/10.3390/app12010136
Recommended Citation
MDPI and ACS Style Ullah, I.; Rios, A.; Gala, V.; Mckeever, S. Explaining Deep Learning Models for Tabular Data Using Layer-Wise Relevance Propagation. Appl. Sci. 2022, 12, 136. https://doi.org/10.3390/app12010136 AMA Style Ullah I, Rios A, Gala V, Mckeever S. Explaining Deep Learning Models for Tabular Data Using Layer-Wise Relevance Propagation. Applied Sciences. 2022; 12(1):136. https://doi.org/10.3390/app12010136 Chicago/Turabian Style Ullah, Ihsan, Andre Rios, Vaibhav Gala, and Susan Mckeever. 2022. "Explaining Deep Learning Models for Tabular Data Using Layer-Wise Relevance Propagation" Applied Sciences 12, no. 1: 136. https://doi.org/10.3390/app12010136
Funder
Enterprise Ireland
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Publication Details
Ullah, I.; Rios, A.; Gala, V.; Mckeever, S. Explaining Deep Learning Models for Tabular Data Using Layer-Wise Relevance Propagation. Appl. Sci. 2022, 12, 136. https://doi.org/10.3390/app12010136