How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods

Abstract Explaining the inner workings of deep neural network models have received con- siderable attention in recent years. Researchers have attempted to provide human parseable explanations justifying why a model performed a specific classification. Although many of these toolkits are available for use, it is unclear which style of explanation is preferred by end-users, thereby demanding investigation. We performed a cross-analysis Amazon Mechanical Turk study comparing the popular state-of-the-art explanation methods to empirically determine which are better in explaining model decisions. The participants were asked to compare explanation methods across applications spanning image, text, audio, and sensory domains. Among the surveyed methods, explanation-by-example was preferred in all do- mains except text sentiment classification, where LIME's method of annotating input text was preferred. We highlight qualitative aspects of employing the stud- ied explainability methods and conclude with implications for researchers and engineers that seek to incorporate explanations into user-facing deployments.
  • Jeya Vikranth Jeyakumar (UCLA)
  • Joseph Noor (UCLA)
  • Yu-Hsi Cheng (UCLA)
  • Luis Garcia (UCLA)
  • Mani Srivastava (UCLA)
Date Dec-2020
Venue Neural Information Processing Systems Online Conference 2020 [link]