A Survey on Neural Network Interpretability
This survey is significant for researchers and practitioners in deep learning who are grappling with the lack of transparency and trust in AI systems, offering a structured overview and new categorization of the field.
This survey paper addresses the growing concern about the black-box nature of deep neural networks by providing a comprehensive review of neural network interpretability research. It clarifies the definition of interpretability, proposes a novel 3D taxonomy for existing approaches, and summarizes evaluation methods, suggesting future research directions.
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.