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.
1 August 2018 in Future Generation Computer Systems
A graph can represent a complex organization of data in which dependencies exist between multiple entities or activities. Such complex structures create challenges for machine learning algorithms, particularly when combined with the high dimensionality of data in current applications. Graph convolutional networks were introduced to adopt concepts from deep convolutional networks (i.e. the convolutional operations/layers) that have shown good results. In this context, we propose two major enhancements to two of the existing graph convolutional network frameworks: (1) topological information enrichment through clustering coefficients; and (2) structural redesign of the network through the addition of dense layers. Furthermore, we propose minor enhancements using convex combinations of activation functions and hyper-parameter optimization. We present extensive results on four state-of-art benchmark datasets. We show that our approach achieves competitive results for three of the datasets and state-of-the-art results for the fourth dataset while having lower computational costs compared to competing methods.
Emotions play a crucial role in human interaction and healthcare. This study introduces an automatic emotion recognition system based on deep learning using electroencephalogram signals. A lightweight pyramidal one-dimensional convolutional neural network model is proposed that involves a small number of learnable parameters. Using the model, a two-level ensemble classifier is designed. Each channel is scanned incrementally in the first level to generate predictions, which are fused using the majority vote. The second level fuses the predictions of all the channels of a signal using a majority vote to predict the emotional state. The method was validated using the public domain challenging benchmark dataset. The electroencephalogram signals over five brain regions were analyzed. The results indicate that the frontal brain region plays a dominant role in two emotion recognition problems (distinguishing high valence vs. low valence and high arousal vs. low arousal states).