Papers must be written in English and formatted according to the Springer Lecture Notes in Computer Science (LNCS) guidelines following the style of the main conference (format).

The maximum length of either research or position papers is 14 pages references excluded. Overlength papers will be rejected without review (papers with smaller page margins and font sizes than specified in the author instructions and set in the style files will also be treated as overlength).

Authors who submit their work to XKDD 2023 commit themselves to present their paper at the workshop in case of acceptance. XKDD 2023 considers the author list submitted with the paper as final. No additions or deletions to this list may be made after paper submission, either during the review period, or in case of acceptance, at the final camera ready stage.

Condition for inclusion in the post-proceedings is that at least one of the co-authors has presented the paper at the workshop. Pre-proceedings will be available online before the workshop.

All accepted papers will be published as post-proceedings in LNCSI and included in the series name Lecture Notes in Computer Science.

All papers for XKDD 2023 must be submitted by using the on-line submission system at CMT.

Although ECML PKDD 2023 will guarantee a streaming service in all rooms and satellite events, this year's organization aims to maximize engagement and physical presence in Turin. The provided streaming service, with the associated remote registration fee, is considered an option only for non-presenting attendees. The goal is to avoid having little participation in the rooms, with the events happening almost exclusively "virtually." Therefore, we will adopt the same rules as the main event also for our workshop: at least one author of each accepted paper must have a full registration and be in Turin to present the paper. Papers without a full registration or in-presence presentation won't be included in the post-workshop Springer proceedings.

• Paper Submission deadline: June 20 June 27, 2023
• Accept/Reject Notification: July 13 June 19, 2023
• Camera-ready deadline: July 31, 2023
• Workshop: September 18, 2023

Program Chairs

Riccardo Guidotti

KDD Lab, University of Pisa, Italy

Francesca Naretto

KDD Lab, University of Pisa, Italy

Tania Cerquitelli

Politecnico di Torino, Italy

Przemyslaw Biecek

MiNI, Warsaw University of Technology, Poland

Daniele Regoli

Intesa Sanpaolo S.p.A., Italy

Invited Speakers

Andreas Theissler

Professor at Aalen University of Applied Sciences, Aalen, Germany

Explainable AI: how far we have come and what’s left for us to do

The research field of explainable AI has gained importance over the previous years. In many cases, interpretable and trustworthy AI is desired. This invited talk will start by briefly surveying and categorizing the field. As the main contribution, the talk’s focus will be on discussing open issues and research questions: some of them in accordance with previous literature, other questions will be raised by taking a higher-level perspective. This aims to inspire discussions, to deduce new ideas, to identify research topics. Overall, the talk aims to contribute to the workshop by showing open research fields in the hope to form a research landscape.

---

Andreas Theissler is a full professor at Aalen University of Applied Sciences in Germany, where he researches and lectures on different aspects of Machine Learning and Human-Centered AI. He received his PhD from Brunel University London in 2014, prior to that he studied Software Engineering and has worked in different Data Science positions in industry. He is interested in different aspects of machine learning, e.g. the interplay, for example on the questions of how we can evaluate, understand, improve, or enable Machine Learning by incorporating expert knowledge. In addition, he has worked in the field of machine learning in applications, e.g. anomaly detection for automotive data. He has published papers on interpretability, efficient data labeling by combining ML models and user interaction, anomaly detection, and on machine learning in applications.

Stefano Teso

Stefano Teso is a tenure-track Assistant Professor at the University of Trento.

The Blessing and Curse of Concepts in Explainable AI and Interactive Machine Learning

Explanations have gained an increasing level of interest in the AI and Machine Learning (ML) communities in order to improve model transparency and allow users to form a mental model of a trained ML model. However, explanations can go beyond this one way communication as a mechanism to elicit user control, because once users understand, they can then provide feedback. The goal of this talk is to give an accessible overview of research where explanations are combined with interactive capabilities as a mean to learn new models from scratch and to edit and debug existing ones, and on the new challenges that this brings forth, with a focus on the problem of aligning humans and machines in the context of human-interpretable representation learning.

---

Stefano Teso is a tenure-track Assistant Professor at the University of Trento whose research lies at the intersection of explainable AI, interactive machine learning, neuro-symbolic AI, representation learning, constraint learning, and preference elicitation. Stefano co-organized tutorials and workshops on (explainable) interactive machine learning and constraint learning at major international conferences (AAAI, IJCAI, ECML-PKDD). He is a regular PC/SPC at ICML, NeurIPS, ICLR, UAI, AAAI, IJCAI, ECML-PKDD and an AC at AISTATS.

Program Committee

• Miguel Couceiro, Université de Lorraine, France
• Alessandro Castelnovo, Intesa San Paolo, Italy
• Riccardo Crupi, Intesa San Paolo, Italy
• Josep Domingo-Ferrer, Universitat Rovira i Virgili, Spain
• Françoise Fessant, Orange Labs, France
• Salvatore Greco, Politecnico di Torino, Italy
• Andreas Holzinger, Medical University of Graz, Austria
• Paulo Lisboa, Liverpool John Moores University, UK
• Marcin Luckner, Warsaw University of Technology, Poland
• Amedeo Napoli, CNRS, France
• John Mollas, Aristotle University of Thessaloniki, Greece
• Enea Parimbelli, University of Pavia, Italy
• Francesca Pratesi, ISTI-CNR, Italy
• Roberto Prevete, University of Napoli, Italy
• Antonio Rago, Imperial College London, UK
• Eliana Pastor, Politecnico di Torino, Italy
• Jan Ramon, Inria, France
• Xavier Renard, AXA, France
• Mahtab Sarvmaili, Dalhousie University, Canada
• Udo Schlegel, Konstanz University, Germany
• Mattia Setzu, University of Pisa, Italy
• Dominik Slezak, University of Warsaw, Poland
• Myra Spiliopoulou, University Magdeburg, Germany
• Francesco Spinnato, Scuola Noramle Superiore, Italy
• Grigorios Tsoumakas, Aristotle University of Thessaloniki, Greece
• Genoveva Vargas-Solar, CNRS, LIRIS, France
• Albrecht Zimmermann, Université de Caen, France