International Workshop on Explainable and Interpretable Machine Learning (XI-ML)
We are pleased to announce the second International Workshop on Explainable and Interpretable Machine Learning (XI-ML)
co-located with KI 2022, Sept. 21, 2022, Trier, Germany.
Submission deadline (extended): July 29, 2022 (23:59 AoE Time).
Objectives
With the current scientific discourse on explainable AI (XAI), algorithmic transparency, interpretability, accountability and finally explainability of algorithmic models and decisions, this workshop on explainable and interpretable machine learning tackles these themes from the modeling and learning perspective; it targets interpretable methods and models being able to explain themselves and their output, respectively. The workshop aims to provide an interdisciplinary forum to investigate fundamental issues in explainable and interpretable machine learning as well as to discuss recent advances, trends, and challenges in this area.
Overall, we are interested in receiving papers related to the following topics which include but are not limited to:
- Rule learning for explainable and interpretable machine learning
- Assessment of interpretable and explainable models
- Cognitive approaches and human concept learning
- Human-centered learning and explanation
- Causality of machine learning models
- Local pattern mining for explanation
- Interpretation of black box models
- Explanation of black box models
- Model-agnostic explanation
- Case-based explanation
- Evaluation metrics
- Empirical research on explainability
- Regulations and legal aspects of XAI
- Applications of all of the above
Program
- 9:00-9:05 Opening
- Session 1: Explanation & Methods
- 9:05-9:30 Jacqueline Höllig, Steffen Thoma and Cedric Kulbach: Evolutionary Counterfactual Visual Explanation
- 9:30-9:55 Sarem Seitz: Self-explaining variational Gaussian Processes for transparency and modelling of prior knowledge
- 9:55-10:20 Thorsten Zylowski: Study on Criteria for Explainable AI for Laypeople
- Session 2: Explanation & Application
- 10:30-10:55 Manuel Eberhardinger, Johannes Maucher and Setareh Maghsudi: Imitation Learning of Logical Program Policies for Multi-Agent Reinforcement Learning
- 10:55-11:20 Ahmad Mel and Tijl De Bie: Mining Interesting Outlier Subgraphs In Attributed Graphs
- 11:20-11:55 Asep Maulana and Martin Atzmueller: Multi-Perspective Anomaly Detection on Bipartite Multi-Layer Social Interaction Networks
- 11:55-12:00 Closing
Papers: Download here
Submission
We will solicit full papers (up to 12 pages) as well as short papers (up to 6 pages); for submission, the LNI Latex template should be used for all workshop submissions https://github.com/gi-ev/LNI.
All submitted papers must
- be written in English;
- contain author names, affiliations, and email addresses;
- be formatted according to the LNI Latex template (use the 1-column style): https://github.com/gi-ev/LNI;
- be in PDF; make sure that the PDF can be viewed on any platform
Authors should chose the workshop as a track of the conference when submitting through the Easy Chair System: https://easychair.org/conferences/?conf=ki2022 (Please choose Track W5: Explainable and Interpretable Machine Learning)
After the KI2022 conference, we intend to publish the proceedings in the CEUR Workshop Proceedings series or GI Lecture Notes in Informatics. Both are indexed in Scopus and DBLP. We will also consider publishing a selection of extended papers in a special issue of an international journal.Important dates
- Submission Deadline (extended): Jul 29, 2022 (23:59 AoE Time)
- Notification of Acceptance: Aug 03, 2022
- Camera-Ready Versions Due: Aug 17, 2022
- Workshop date: September 21, 2022 (tentative, to be confirmed)
Committee
Workshop Chairs
- Martin Atzmueller, Osnabrück University & DFKI, Germany
- Tomáš Kliegr, University of Economics Prague, Czech Republic
- Ute Schmid, University of Bamberg, Germany
Program Committee
- Klaus-Dieter Althoff, University of Hildesheim & DFKI
- Henrik Boström, KTH Royal Institute of Technology, Sweden
- Amit Dhurandhar, IBM TJ Watson Research Center, USA
- Johannes Fürnkranz, Johannes Kepler University, Linz
- Martin Holena, Czech Academy of Sciences
- Stefano Teso, KU Leuven, Belgium
- Filip Zelezny, Czech Technical University
Contact
If you have questions regarding the workshop, please contact Martin Atzmueller: martin.atzmueller@uni-osnabrueck.de