Interpreting Multivariate Shapley Interactions in DNNs

Hao Zhang, Yichen Xie, Longjie Zheng, Die Zhang, Quanshi Zhang

AAAI 2021 pp. 10877-10886

doi:10.1609/AAAI.V35I12.17299 /aaai/2021/zhang2021aaai-interpreting/

Abstract

This paper aims to explain deep neural networks (DNNs) from the perspective of multivariate interactions. In this paper, we define and quantify the significance of interactions among multiple input variables of the DNN. Input variables with strong interactions usually form a coalition and reflect prototype features, which are memorized and used by the DNN for inference. We define the significance of interactions based on the Shapley value, which is designed to assign the attribution value of each input variable to the inference. We have conducted experiments with various DNNs. Experimental results have demonstrated the effectiveness of the proposed method.

PDF AAAI Semantic Scholar

Cite

Text

Zhang et al. "Interpreting Multivariate Shapley Interactions in DNNs." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I12.17299

Markdown

[Zhang et al. "Interpreting Multivariate Shapley Interactions in DNNs." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/zhang2021aaai-interpreting/) doi:10.1609/AAAI.V35I12.17299

BibTeX

@inproceedings{zhang2021aaai-interpreting,
  title     = {{Interpreting Multivariate Shapley Interactions in DNNs}},
  author    = {Zhang, Hao and Xie, Yichen and Zheng, Longjie and Zhang, Die and Zhang, Quanshi},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {10877-10886},
  doi       = {10.1609/AAAI.V35I12.17299},
  url       = {https://mlanthology.org/aaai/2021/zhang2021aaai-interpreting/}
}