Logic Constraints to Feature Importances

10/13/2021
by   Nicola Picchiotti, et al.
0

In recent years, Artificial Intelligence (AI) algorithms have been proven to outperform traditional statistical methods in terms of predictivity, especially when a large amount of data was available. Nevertheless, the "black box" nature of AI models is often a limit for a reliable application in high-stakes fields like diagnostic techniques, autonomous guide, etc. Recent works have shown that an adequate level of interpretability could enforce the more general concept of model trustworthiness. The basic idea of this paper is to exploit the human prior knowledge of the features' importance for a specific task, in order to coherently aid the phase of the model's fitting. This sort of "weighted" AI is obtained by extending the empirical loss with a regularization term encouraging the importance of the features to follow predetermined constraints. This procedure relies on local methods for the feature importance computation, e.g. LRP, LIME, etc. that are the link between the model weights to be optimized and the user-defined constraints on feature importance. In the fairness area, promising experimental results have been obtained for the Adult dataset. Many other possible applications of this model agnostic theoretical framework are described.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/07/2022

Explainable Artificial Intelligence (XAI) for Internet of Things: A Survey

Black-box nature of Artificial Intelligence (AI) models do not allow use...
research
04/18/2018

Visualizing the Feature Importance for Black Box Models

In recent years, a large amount of model-agnostic methods to improve the...
research
12/29/2021

Towards a Shapley Value Graph Framework for Medical peer-influence

eXplainable Artificial Intelligence (XAI) is a sub-field of Artificial I...
research
01/22/2022

Artificial Intelligence for Suicide Assessment using Audiovisual Cues: A Review

Death by suicide is the seventh of the leading death cause worldwide. Th...
research
01/05/2023

Semantic match: Debugging feature attribution methods in XAI for healthcare

The recent spike in certified Artificial Intelligence (AI) tools for hea...

Please sign up or login with your details

Forgot password? Click here to reset