The rising popularity of explainable artificial intelligence (XAI) to understand high-performing
black boxes raised the question of how to evaluate explanations of machine learning (ML) …

Explainable Artificial Intelligence (XAI) has experienced a significant growth over the last few
years. This is due to the widespread application of machine learning, particularly deep …

Deep learning methods are achieving ever-increasing performance on many artificial
intelligence tasks. A major limitation of deep models is that they are not amenable to …

We consider the problem of explaining the predictions of graph neural networks (GNNs),
which otherwise are considered as black boxes. Existing methods invariably focus on …

Dramatic success in machine learning has led to a new wave of AI applications (for
example, transportation, security, medicine, finance, defense) that offer tremendous benefits …

In recent years, to mitigate the problem of fake news, computational detection of fake news
has been studied, producing some promising early results. While important, however, we …

Techniques for interpretable machine learning Page 1 68 COMMUNICATIONS OF THE
ACM | JANUARY 2020 | VOL. 63 | NO. 1 review articles MACHINE LEARNING IS …

The need for interpretable and accountable intelligent systems grows along with the
prevalence of artificial intelligence (AI) applications used in everyday life. Explainable AI …

Machine and deep learning have proven their utility to generate data-driven models with
high accuracy and precision. However, their non-linear, complex structures are often difficult …

Recently, a significant amount of research has been investigated on interpretation of deep
neural networks (DNNs) which are normally processed as black box models. Among the …