Declarative Reasoning on Explanations Using Constraint Logic Programming

1 code implementation • 1 Sep 2023 • Laura State, Salvatore Ruggieri, Franco Turini

Explaining opaque Machine Learning (ML) models is an increasingly relevant problem.

Common Sense Reasoning

Reason to explain: Interactive contrastive explanations (REASONX)

1 code implementation • 29 May 2023 • Laura State, Salvatore Ruggieri, Franco Turini

REASONX provides interactive contrastive explanations that can be augmented by background knowledge, and allows to operate under a setting of under-specified information, leading to increased flexibility in the provided explanations.

Beyond Demographic Parity: Redefining Equal Treatment

no code implementations • 14 Mar 2023 • Carlos Mougan, Laura State, Antonio Ferrara, Salvatore Ruggieri, Steffen Staab

Liberalism-oriented political philosophy reasons that all individuals should be treated equally independently of their protected characteristics.

Fairness Philosophy

Explainability in Practice: Estimating Electrification Rates from Mobile Phone Data in Senegal

1 code implementation • 11 Nov 2022 • Laura State, Hadrien Salat, Stefania Rubrichi, Zbigniew Smoreda

We conclude our paper by pointing to the two main challenges we encountered during our work: data processing and model design that might be restricted by currently available XAI methods, and the importance of domain knowledge to interpret explanations.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1