LioNets: A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Information

TL;DR

This paper introduces LioNets, a neural-specific local interpretation method for textual and time-series data, enhancing explainability in AI systems by providing feature importance and counterfactual explanations.

Contribution

It proposes a novel local interpretation technique tailored for neural models, with new feature importance presentation and counterfactual generation methods, along with an improved evaluation metric.

Findings

Effective feature importance explanations for neural models.

Generation of counterfactual words on textual data.

Enhanced evaluation metrics for interpretability quality.

Abstract

Artificial Intelligence (AI) has a tremendous impact on the unexpected growth of technology in almost every aspect. AI-powered systems are monitoring and deciding about sensitive economic and societal issues. The future is towards automation, and it must not be prevented. However, this is a conflicting viewpoint for a lot of people, due to the fear of uncontrollable AI systems. This concern could be reasonable if it was originating from considerations associated with social issues, like gender-biased, or obscure decision-making systems. Explainable AI (XAI) is recently treated as a huge step towards reliable systems, enhancing the trust of people to AI. Interpretable machine learning (IML), a subfield of XAI, is also an urgent topic of research. This paper presents a small but significant contribution to the IML community, focusing on a local-based, neural-specific interpretation process applied to textual and time-series data. The proposed methodology introduces new approaches to the presentation of feature importance based interpretations, as well as the production of counterfactual words on textual datasets. Eventually, an improved evaluation metric is introduced for the assessment of interpretation techniques, which supports an extensive set of qualitative and quantitative experiments.