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 axioms of sensitivity and implementation invariance to ensure the validity and reliability of attribution results. Yet, the existing attribution methods present challenges for effective interpretation and efficient computation. In this work, we introduce MFABA, an attribution algorithm that adheres to axioms, as a novel method for interpreting DNN. Additionally, we provide the theoretical proof and in-depth analysis for MFABA algorithm, and conduct a large scale experiment. The results demonstrate its superiority by achieving over 101.5142 times faster speed than the state-of-the-art attribution algorithms. The effectiveness of MFABA is thoroughly evaluated through the statistical analysis in comparison to other methods, and the full implementation package is open-source at: https://github.com/LMBTough/MFABA
@article{arxiv.2312.13630,
title = {MFABA: A More Faithful and Accelerated Boundary-based Attribution Method for Deep Neural Networks},
author = {Zhiyu Zhu and Huaming Chen and Jiayu Zhang and Xinyi Wang and Zhibo Jin and Minhui Xue and Dongxiao Zhu and Kim-Kwang Raymond Choo},
journal= {arXiv preprint arXiv:2312.13630},
year = {2023}
}
Comments
Accepted by The 38th Annual AAAI Conference on Artificial Intelligence (AAAI-24)