Concept-based Explainable AI (C-XAI): a paradigm shift in XAI

Speaker: Gabriele Ciravegna, Politecnico di Torino

Abstract: The field of eXplainable Artificial Intelligence (XAI) emerged in response to the growing need for more transparent and reliable models. However, using raw features to provide explanations has been discussed in several works lately, advocating for more user-understandable explanations.  To address this issue, a wide range of papers proposed Concept-based XAI (C-XAI) methods have been published in recent years. Nevertheless, a unified categorization and precise field definition are still missing. In this talk, we will try to fill the gap through a review of C-XAI approaches. We will identify and define what is a concept and a concept-based explanation. We will then provide guidelines for selecting a suitable category based on the application context. Additionally, we will analyse three prominent proposals focusing on supervised concept-based model. We will see that embedded representations of the concepts overcome the limit in the representation capability of concept-bottleneck models without preventing to provide interpretable predictions.

Biography: Gabriele Ciravegna is a Postdoctoral Researcher at Politecnico di Torino, with a dedicated focus on advancing Artificial Intelligence. Gabriele's work aims to enhance the comprehensibility, reliability, and robustness of neural networks. Since 2019, he has been an active contributor, regularly publishing and serving as a reviewer in prestigious conferences and journals of the field, such as Neurips, ICML, AAAI, IJCAI, IEEE TPAMI, IEEE TNNLS.
For his contributions to the field of 'Concept-based Explainable AI,' he has been invited to speak on the topic at several venues. Gabriele completed his Ph.D. under the guidance of Prof. Marco Gori, earning the IEEE Caianiello Award for Best Ph.D. Thesis in 2023. Since 2022, he has been teaching Machine Learning courses at both Politecnico di Torino and the Université Côte d'Azur, where he also completed his first postdoctoral fellowship.

Host: Pietro Barbiero, Antonietta Mira