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

Document Type

Conference Item

Publication Date

1-1-2024

Abstract

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.

Divisions

universiti

Publisher

ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE

Publisher Location

2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA

Event Title

38th Annual AAAI Conference on Artificial Intelligence, Vol 38 No 15

Event Location

Vancouver, CANADA

Event Dates

20-27 February 2024

Event Type

conference

Additional Information

38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence, Vancouver, CANADA, FEB 20-27, 2024

This document is currently not available here.

Share

COinS