A Concept and Argumentation based Interpretable Model in High Risk Domains

TL;DR

This paper introduces CAM, a novel interpretable AI model for high-risk domains that leverages human-understandable concepts and argumentation for transparent decision-making, achieving competitive accuracy.

Contribution

The paper presents a new concept mining and argumentation-based framework that enhances interpretability by incorporating human knowledge into AI models for high-risk applications.

Findings

CAM is transparent and interpretable with human-coherent knowledge.

CAM achieves competitive predictive performance.

The model provides dialogical explanations with reasoning paths.

Abstract

Interpretability has become an essential topic for artificial intelligence in some high-risk domains such as healthcare, bank and security. For commonly-used tabular data, traditional methods trained end-to-end machine learning models with numerical and categorical data only, and did not leverage human understandable knowledge such as data descriptions. Yet mining human-level knowledge from tabular data and using it for prediction remain a challenge. Therefore, we propose a concept and argumentation based model (CAM) that includes the following two components: a novel concept mining method to obtain human understandable concepts and their relations from both descriptions of features and the underlying data, and a quantitative argumentation-based method to do knowledge representation and reasoning. As a result of it, CAM provides decisions that are based on human-level knowledge and the reasoning process is intrinsically interpretable. Finally, to visualize the purposed interpretable model, we provide a dialogical explanation that contain dominated reasoning path within CAM. Experimental results on both open source benchmark dataset and real-word business dataset show that (1) CAM is transparent and interpretable, and the knowledge inside the CAM is coherent with human understanding; (2) Our interpretable approach can reach competitive results comparing with other state-of-art models.