Topics

Hybrid Learning and Reasoning

Seminar an der Universität des Saarlandes, Fachrichtung Informatik, LSF 143206

The topics for seminar time slots (see schedule) are as follows. Currently assigned topics are marked in red. Selected background literature is indicated below; topic reference papers are available in the web or on request from seminar organizers.

Topic #	Topic
1	Relational Neural Machines (I) Marra, G. et al. (2020): Relational Neural Machines. Proc. 24th European Conference on Artificial Intelligence (ECAI). [paper, supp]
2	Relational Neural Machines (II) Carraro, T. et al. (2023): Logic Tensor Networks for Top-N Recommendation. Proc. 16th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy). CEUR 3212. [paper, supp]
3	Relational Neural Machines (III) Umili, E., Capobianco, R., & Giacomo, G. D. (2022): Grounding LTLf Specifications in Images. Proc. 16th International Workshop on Neural-Symbolic Learning and Reasoning. CEUR 3212.[paper]
4	Deep Deductive Reasoning Ebrahimi, M. et al. (2021): Neuro-Symbolic Deductive Reasoning for Cross-Knowledge Graph Entailment. Proc. AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering. CEUR 2846. [paper, supp]
5	Causal Representation Learning Karimi, A.-H. et al. (2022): Towards Causal Algorithmic Recourse. Proc. International Workshop XxAI - Beyond Explainable AI. Springer. [paper, supp]
6	Graph Reinforcement Learning Wang, J. et al. (2020): Multi-Agent Graph Reinforcement Learning for Connected Automated Driving. Proc. 37th International Conference on Machine Learning (ICML). [paper, supp]
7	Learning for Planning (I) O'Toole, S. et al. (2022): Sampling from Pre-Images to Learn Heuristic Functions for Classical Planning. Proc. International Symposium on Combinatorial Search. AAAI. [paper, supp]
8	Learning for Planning (II) Pusse, F. & Klusch, M. (2019): Hybrid Online POMDP Planning and Deep Reinforcement Learning for Safer Self-Driving Cars. Proc. 30th IEEE International Intelligent Vehicles Symposium (IV). [paper, supp]
9	Learning for Planning (III) Lamanna, L. et al. (2021): Online Learning of Action Models for PDDL Planning. Proc. International Joint Conference on AI (IJCAI).[paper, supp]

Selected background references:

Garcez, A. D. A., & Lamb, L. C. (2023). Neurosymbolic AI: The 3^rd Wave. Artificial Intelligence Review, 1-20.
Mossakowski, T. (2022). Modular Design Patterns for Neural-symbolic Integration: Refinement and Combination. Proceedings of the 16th International Workshop on Neural-Symbolic Learning and Reasoning. CEUR.3212
van Bekkum, M., de Boer, M., van Harmelen, F. et al. (2021): Modular design patterns for hybrid learning and reasoning systems: A taxonomy, patterns and use cases. Applied Intelligence.
van Harmelen, F. & Teije, A.T. (2019). A Boxology of Design Patterns for Hybrid Learning and Reasoning Systems. Journal of Web Engineering, 18(1-3). https://arxiv.org/pdf/1905.12389.pdf
Battaglia, et al. (2018): Relational Inductive Biases, Deep Learning, and Graph Networks. arXiv:1806.01261.
Lamb, L.C. et al. (2020): Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective. Proc. IJCAI
Schölkopf, B., Locatello, F., Bauer, S., Ke, N. R., Kalchbrenner, N., Goyal, A., & Bengio, Y. (2021): Toward Causal Representation Learning. Proceedings of the IEEE, 109(5):612–634.
International Workshop Series on Neural-Symbolic Learning and Reasoning (since 2005): http://www.neural-symbolic.org/