Explaining Deep Learning Models for Structured Data using Layer-Wise Relevance Propagation
This work addresses the challenge of providing clear and computationally efficient explanations for deep learning models on structured data, which is crucial for building trust and enabling real-time applications for practitioners in various domains.
This paper applies Layer-wise Relevance Propagation (LRP), an explainability technique, to structured datasets using a 1D-CNN for credit card fraud detection and telecom customer churn prediction. The authors demonstrate that LRP is more effective than LIME and SHAP for explainability, both locally and holistically, and offers a significant computational time advantage (1-2s vs. 22s for LIME and 108s for SHAP).
Trust and credibility in machine learning models is bolstered by the ability of a model to explain itsdecisions. While explainability of deep learning models is a well-known challenge, a further chal-lenge is clarity of the explanation itself, which must be interpreted by downstream users. Layer-wiseRelevance Propagation (LRP), an established explainability technique developed for deep models incomputer vision, provides intuitive human-readable heat maps of input images. We present the novelapplication of LRP for the first time with structured datasets using a deep neural network (1D-CNN),for Credit Card Fraud detection and Telecom Customer Churn prediction datasets. We show how LRPis more effective than traditional explainability concepts of Local Interpretable Model-agnostic Ex-planations (LIME) and Shapley Additive Explanations (SHAP) for explainability. This effectivenessis both local to a sample level and holistic over the whole testing set. We also discuss the significantcomputational time advantage of LRP (1-2s) over LIME (22s) and SHAP (108s), and thus its poten-tial for real time application scenarios. In addition, our validation of LRP has highlighted features forenhancing model performance, thus opening up a new area of research of using XAI as an approachfor feature subset selection