A Survey on Neural Network Interpretability

doi:10.1109/TETCI.2021.3100641

Paper

A Survey on Neural Network Interpretability

Published Dec 28, 2020 · Yu Zhang, P. Tiňo, A. Leonardis

IEEE Transactions on Emerging Topics in Computational Intelligence

Q1 SJR score

521

Citations

17

Influential Citations

Full text Semantic Scholar

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.

Highly Cited

Study Snapshot

Key takeawayThis survey reviews neural network interpretability research and proposes a novel taxonomy to better understand and evaluate the black-box nature of deep learning systems.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

A Survey on Neural Network Interpretability

References

Citations