KI Schedule

Joint Session: Inf-Turing

KM, KDML, DB

• 14:30 - 14:55: Malte Luttermann, Ralf Möller and Mattis Hartwig - Towards Privacy-Preserving Relational Data Synthesis via Probabilistic Relational Models
• 14:55 - 15:10: Andrey Okhotin, Dmitry Molchanov, Vladimir Arkhipkin, Grigory Bartosh, Viktor Ohanesian, Aibek Alanov and Dmitry Vetrov - Star - Shaped Denoising Diffusion Probabilistic Models
• 15:10 - 15:35: Christopher Bonenberger, Markus Schneider, Wolfgang Ertel and Friedhelm Schwenker - A Note on Linear Time Series Prediction
• 15:35 - 16:00: Wilson Sentanoe, Sreyashi Saha, Yasas Diyanananda, Aqsa Manzoor, Buddhika Dasanayake and Daniela Thyssens - Graph2RETA: Graph Neural Networks for Pick-up and Delivery Route Prediction and Arrival Time Estimation

Session 2: Visual and Acoustic Approaches
Session Chair: Ulrich Furbach

• 16:30 - 16:55: Ilira Troshani, Thiago Gouvêa and Daniel Sonntag - Leveraging Weakly Supervised and Multiple Instance Learning for Multi-label Classification of Passive Acoustic Monitoring Data
• 16:55 - 17:20: Hannes Kath, Thiago S. Gouvêa and Daniel Sonntag - Active Learning in Multi-label Classification of Bioacoustic Data
• 17:20 - 17:35: Vanessa Borst, Timo Dittus, Konstantin Müller and Samuel Kounev - Early Explorations of Lightweight Neural Networks for Wound Segmentation on Mobile Devices
• 17:35 - 17:50: Christian Beecks, Anandraj Amalraj, Alexander Graß, Marc Jentsch, Felix Kitschke, Maximilian Norz and Patric Schäffer - Leveraging YOLO for Real-Time Video Analysis of Animal Welfare in Pig Slaughtering Processes

Session 3: Data Sets and Data Handling
Session Chair: Ralf Möller

• 09:00 - 09:25: Björn Filter, Ralf Möller and Özgür Özçep - Mechanisms for Data Sharing in Collaborative Causal Inference
• 09:25 - 09:50: Sami Kharma and Jürgen Großmann - Image Dataset Quality Assessment Through Descriptive Out-of-Distribution Detection
• 09:50 - 10:05: Julian Haasis, Christopher Bonenberger and Markus Schneider - Instance segmentation with a novel tree log detection dataset
• 10:05 - 10:20: Hannes Kath, Thiago S. Gouvêa and Daniel Sonntag - A Human-in-the-Loop Tool for Annotating Passive Acoustic Monitoring Datasets
• 10:20 - 10:35: Andreea Iana, Goran Glavaš and Heiko Paulheim - MIND Your Language: A Multilingual Dataset for Cross-lingual News Recommendation

Session 4: Explainability
Session Chair: Bernhard Nebel

• 11:00 - 11:25: Nils Kemmerzell and Annika Schreiner - Quantifying the Trade-Offs between Dimensions of Trustworthy AI - An Empirical Study on Fairness, Explainability, Privacy, and Robustness
• 11:25 - 11:50: Julian Tritscher, Maximilian Wolf, Anna Krause, Andreas Hotho and Daniel Schlör - Data Generation for Explainable Occupational Fraud Detection
• 11:50 - 12:05: Maximilian Noppel and Christian Wressnegger - A Brief Systematization of Explanation-Aware Attacks
• 12:05 - 12:20: Aray Karjauv and Sahin Albayrak - LaFAM: Unsupervised Feature Attribution with Label-free Activation Maps
• 12:20 - 12:35: Emanuel Slany, Stephan Scheele and Ute Schmid - Explanatory Interactive Machine Learning with Counterexamples from Constrained Large Language Models

Session 5: AI in Practice
Session Chair:  Stefan Edelkamp

• 14:00 - 14:25: Justus Fries, Michael Freund and Andreas Harth - SaVeWoT: Scripting and Verifying Web of Things Systems and Their Effects on the Physical World
• 14:25 - 14:50: Jan Roßbach, Oliver De Candido, Ahmed Hammam, and Michael Leuschel - Evaluating AI-based Components for Autonomous Railway Systems
• 14:50 - 15:15: Anna Kruspe and Mila Stillman - Saxony-Anhalt is the worst: Bias towards German federal states in Large Language Models
• 15:15 - 15:40: Claudia Schon and Oliver Jakobs - Context-Specific Selection of Commonsense Knowledge Using Large Language Models

Session 6: AI and Games
Session Chair: Benjamin Paaßen

• 16:00 - 16:25: Stefan Edelkamp - Could the Declarer have Discarded It? Refined Anticipation of Cards in Skat
• 16:25 - 16:50: Timo Bertram, Johannes Fürnkranz and Martin Müller - Efficiently Training Neural Networks for Imperfect-Information Games by Sampling Information Sets
• 16:50 - 17:15: Stefan Edelkamp - A Framework for General Trick-Taking Card Games

19:00 - Champagne Reception

19:30 - Conference Dinner

Invited Speaker: Christian Bauckhage
Inf-Turing
Quantum AI / ML – Hype or Hope?

Session 7: Symbolic Approaches
Session Chair: Hagen Peukert

• 10:30 - 10:55: Julia Ruttmann and Alexander Schiendorfer - SocialCOP: Reusable Building Blocks for Collective Constraint Optimization
• 10:55 - 11:20: Moritz Bayerkuhnlein, Tobias Schwartz and Diedrich Wolter - From Resolving Inconsistencies in Qualitative Constraints Networks to Identifying Robust Solutions: A Universal Encoding in ASP
• 11:20 - 11:35: Konstantin Kirchheim, Tim Gonschorek and Frank Ortmeier - Out-of-Distribution Detection with Logical Reasoning

Session 8: Reinforcement Learning
Session Chair: Magda Gregorová

• 12:00 - 12:25: Xuzhe Dang and Stefan Edelkamp - Data Augmentation in Latent Space with Variational Autoencoder and Pretrained Image Model for Visual Reinforcement Learning
• 12:25 - 12:40: Quirin Göttl, Haris Asif, Alexander Mattick, Robert Marzilger, Axel Plinge - Automated Design in Hybrid Action Spaces by Reinforcement Learning and Differential Evolution
• 12:40 - 12:55: Anna Riedmann, Julia Götz, Carlo D’Eramo and Birgit Lugrin - Uli-RL: A Real-World Deep Reinforcement Learning Pedagogical Agent for Children