MFABA: A More Faithful and Accelerated Boundary-Based Attribution Method for Deep Neural Networks

To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each input dimension to indicate its importance towards the model outcome. Notably, the attribution methods use the ax- ioms of sensitivity and implementation invariance to ensure the validity and reliability of attribution results. Yet, the ex- isting attribution methods present challenges for effective in- terpretation and efficient computation. In this work, we in- troduce MFABA, an attribution algorithm that adheres to ax- ioms, as a novel method for interpreting DNN. Addition- ally, we provide the theoretical proof and in-depth analy- sis for MFABA algorithm, and conduct a large scale exper- iment. The results demonstrate its superiority by achieving over 101.5142 times faster speed than the state-of-the-art at- tribution algorithms. The effectiveness of MFABA is thor- oughly evaluated through the statistical analysis in compar- ison to other methods, and the full implementation package is open-source at: https://github.com/LMBTough/MFABA.

Authors

• Zhiyu Zhu The University of Sydney
• Huaming Chen School of Electrical and Computer Engineering, University of Sydney, Australia
• Jiayu Zhang SuZhouYierqi
• Xinyi Wang
• Zhibo Jin The University of Sydney
• Minhui Xue CSIRO's Data61, Sydney 2015, Australia
• Dongxiao Zhu Wayne State University
• Kim-Kwang Raymond Choo University of Texas at San Antonio

Keywords

• CV: Interpretability, Explainability, and Transparency
• ML: Adversarial Learning & Robustness
• ML: Transparent, Interpretable, Explainable ML