A Survey on Neural Network Interpretability

Abstract

Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people's trust on deep learning systems. It is also related to many ethical problems, e.g., algorithmic discrimination. Moreover, interpretability is a desired property for deep networks to become powerful tools in other research fields, e.g., drug discovery and genomics. In this survey, we conduct a comprehensive review of the neural network interpretability research. We first clarify the definition of interpretability as it has been used in many different contexts. Then we elaborate on the importance of interpretability and propose a novel taxonomy organized along three dimensions: type of engagement (passive vs. active interpretation approaches), the type of explanation, and the focus (from local to global interpretability). This taxonomy provides a meaningful 3D view of distribution of papers from the relevant literature as two of the dimensions are not simply categorical but allow ordinal subcategories. Finally, we summarize the existing interpretability evaluation methods and suggest possible research directions inspired by our new taxonomy.

This work has been accepted by IEEE-TETCI

References in corpus (17)

• Sequence to Sequence Learning with Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Towards A Rigorous Science of Interpretable Machine Learning
• Methods for Interpreting and Understanding Deep Neural Networks
• Striving for Simplicity: The All Convolutional Net
• Understanding Neural Networks Through Deep Visualization
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• The Loss Surfaces of Multilayer Networks
• Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
• Towards Explainable Artificial Intelligence
• Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
• Prototype selection for interpretable classification
• Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions
• Beyond Sparsity: Tree Regularization of Deep Models for Interpretability
• Mathematics of Deep Learning
• Controlling generative models with continuous factors of variations
• Feature Importance Ranking for Deep Learning

Cited by in corpus (12)

• A Survey on Data-driven Software Vulnerability Assessment and Prioritization
• Synthetic Benchmarks for Scientific Research in Explainable Machine Learning
• DuTrust: A Sentiment Analysis Dataset for Trustworthiness Evaluation
• Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings
• Unsupervised Learning of Neurosymbolic Encoders
• Ensembles of Random SHAPs
• How to Explain Neural Networks: an Approximation Perspective
• Interpretability in Safety-Critical FinancialTrading Systems
• Image recognition via Vietoris-Rips complex
• Interpretable Face Manipulation Detection via Feature Whitening
• Tensorization of neural networks for improved privacy and interpretability
• A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines