Negative Flux Aggregation to Estimate Feature Attributions

01/17/2023
by   Xin Li, et al.
0

There are increasing demands for understanding deep neural networks' (DNNs) behavior spurred by growing security and/or transparency concerns. Due to multi-layer nonlinearity of the deep neural network architectures, explaining DNN predictions still remains as an open problem, preventing us from gaining a deeper understanding of the mechanisms. To enhance the explainability of DNNs, we estimate the input feature's attributions to the prediction task using divergence and flux. Inspired by the divergence theorem in vector analysis, we develop a novel Negative Flux Aggregation (NeFLAG) formulation and an efficient approximation algorithm to estimate attribution map. Unlike the previous techniques, ours doesn't rely on fitting a surrogate model nor need any path integration of gradients. Both qualitative and quantitative experiments demonstrate a superior performance of NeFLAG in generating more faithful attribution maps than the competing methods.

READ FULL TEXT
research
03/02/2023

Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions

Various attribution methods have been developed to explain deep neural n...
research
11/15/2021

Fast Axiomatic Attribution for Neural Networks

Mitigating the dependence on spurious correlations present in the traini...
research
04/22/2020

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

Integrated gradients as an attribution method for deep neural network mo...
research
09/28/2021

Who Explains the Explanation? Quantitatively Assessing Feature Attribution Methods

AI explainability seeks to increase the transparency of models, making t...
research
06/24/2021

Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy

Deep Neural Networks (DNNs) are known to be strong predictors, but their...
research
07/19/2021

Improving Interpretability of Deep Neural Networks in Medical Diagnosis by Investigating the Individual Units

As interpretability has been pointed out as the obstacle to the adoption...
research
07/09/2021

Understanding the Distributions of Aggregation Layers in Deep Neural Networks

The process of aggregation is ubiquitous in almost all deep nets models....

Please sign up or login with your details

Forgot password? Click here to reset