DAX: Deep Argumentative eXplanation for Neural Networks

by   Emanuele Albini, et al.

Despite the rapid growth in attention on eXplainable AI (XAI) of late, explanations in the literature provide little insight into the actual functioning of Neural Networks (NNs), significantly limiting their transparency. We propose a methodology for explaining NNs, providing transparency about their inner workings, by utilising computational argumentation (a form of symbolic AI offering reasoning abstractions for a variety of settings where opinions matter) as the scaffolding underpinning Deep Argumentative eXplanations (DAXs). We define three DAX instantiations (for various neural architectures and tasks) and evaluate them empirically in terms of stability, computational cost, and importance of depth. We also conduct human experiments with DAXs for text classification models, indicating that they are comprehensible to humans and align with their judgement, while also being competitive, in terms of user acceptance, with existing approaches to XAI that also have an argumentative spirit.



page 16

page 17

page 19


Do Human Rationales Improve Machine Explanations?

Work on "learning with rationales" shows that humans providing explanati...

Argumentative XAI: A Survey

Explainable AI (XAI) has been investigated for decades and, together wit...

Transparency and Explanation in Deep Reinforcement Learning Neural Networks

Autonomous AI systems will be entering human society in the near future ...

Argumentative Explanations for Pattern-Based Text Classifiers

Recent works in Explainable AI mostly address the transparency issue of ...

Towards Human-Understandable Visual Explanations:Imperceptible High-frequency Cues Can Better Be Removed

Explainable AI (XAI) methods focus on explaining what a neural network h...

BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations

A key impediment to the use of AI is the lacking of transparency, especi...

Towards Responsible AI for Financial Transactions

The application of AI in finance is increasingly dependent on the princi...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.