Papers accepted at AAAI

We are delighted to announce that 4 papers written by members of our unit have been accepted to AAAI. Congratulations to the authors! In addition, unit member Luiz Chamon is involved in organising a tutorial on “Learning under Requirements: Supervised and Reinforcement Learning with Constraints”.

1. Neural Reasoning About Agents’ Goals, Preferences, and Actions

   Matteo Bortoletto, Lei Shi, Andreas Bulling

   Proc. 38th AAAI Conference on Artificial Intelligence (AAAI), pp. 1–13, 2024.

   Abstract Links BibTeX Project

   We propose the Intuitive Reasoning Network (IRENE) – a novel neural model for intuitive psychological reasoning about agents’ goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state representations with a transformer to encode the task context. When evaluated on the challenging Baby Intuitions Benchmark, IRENE achieves new state-of-the-art performance on three out of its five tasks – with up to 48.9% improvement. In contrast to existing methods, IRENE is able to bind preferences to specific agents, to better distinguish between rational and irrational agents, and to better understand the role of blocking obstacles. We also investigate, for the first time, the influence of the training tasks on test performance. Our analyses demonstrate the effectiveness of IRENE in combining prior knowledge gained during training for unseen evaluation tasks.

   doi:

   Code: https://git.hcics.simtech.uni-stuttgart.de/public-projects/IRENE

   @inproceedings{bortoletto24_aaai, author = {Bortoletto, Matteo and Shi, Lei and Bulling, Andreas}, title = {Neural Reasoning About Agents’ Goals, Preferences, and Actions}, booktitle = {Proc. 38th AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, pages = {1--13}, doi = {} }

2. HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces

   J. Pan, M. Nayyeri, Y. Li, S. Staab

   Proc. 38th AAAI Conference on Artificial Intelligence (AAAI), pp. 1–13, 2024.

   Links BibTeX Project

   doi:

   @inproceedings{pan24_aaai, author = {Pan, J. and Nayyeri, M. and Li, Y. and Staab, S.}, title = {HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces}, booktitle = {Proc. 38th AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, pages = {1--13}, doi = {} }

3. NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning

   B. Xiong, M. Nayyeri, L. Luo, Z. Wang, S. Pan, S. Staab

   Proc. 38th AAAI Conference on Artificial Intelligence (AAAI), pp. 1–13, 2024.

   Links BibTeX Project

   doi:

   @inproceedings{xiong24_aaai, author = {Xiong, B. and Nayyeri, M. and Luo, L. and Wang, Z. and Pan, S. and Staab, S.}, title = {NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning}, booktitle = {Proc. 38th AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, pages = {1--13}, doi = {} }

4. Navigating Open Set Scenarios for Skeleton-based Action Recognition

   K. Peng, Y. Cheng, J. Zheng, R. Liu, D. Schneider, J. Zhang, K. Yang, M. S. Sarfraz, R. Stiefelhagen, A. Roitberg

   Proc. 38th AAAI Conference on Artificial Intelligence (AAAI), pp. 1–13, 2024.

   Links BibTeX Project

   doi:

   @inproceedings{peng24_aaai, author = {Peng, K. and Cheng, Y. and Zheng, J. and Liu, R. and Schneider, D. and Zhang, J. and Yang, K. and Sarfraz, M. S. and Stiefelhagen, R. and Roitberg, A.}, title = {Navigating Open Set Scenarios for Skeleton-based Action Recognition}, booktitle = {Proc. 38th AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, pages = {1--13}, doi = {} }