The 2nd International Workshop on Spatio-Temporal Reasoning and Learning (STRL 2023) was organised as part of the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023), the premier AI Research conference bringing together the international AI community to communicate the advances and achievements of AI research. IJCAI 2023 was held at Macao, China, and the STRL 2023 workshop was held there as a full-day event.
Opposing the false dilemma of logical reasoning vs machine learning, we argue for a synergy between these two paradigms in order to obtain hybrid, humancentred AI systems that will be robust, generalisable, explainable, and ecologically valid. Indeed, it is well-known that machine learning only includes statistical information and, therefore, on its own is inherently unable to capture perturbations (interventions or changes in the environment), or perform explainable reasoning and planning. Ideally, (the training of) machine learning models should be tied to assumptions that align with physics and human cognition to allow for these models to be re-used and re-purposed in novel scenarios. On the other hand, it is also the case that logic in itself can be brittle too, and logic further assumes that the symbols with which it can reason are available a priori. It is becoming ever more evident in the literature that modular AI architectures should be prioritised, where the involved knowledge about the world and the reality that we are operating in is decomposed into independent and recomposable pieces, as such an approach should only increase the chances that these systems behave in a causally sound manner.
The aim of this workshop is to formalize such a synergy between logical reasoning and machine learning that will be grounded on spatial and temporal knowledge. We argue that the formal methods developed within the spatial and temporal reasoning community, be it qualitative or quantitative, naturally build upon (commonsense) physics and human cognition, and could therefore form a module that would be beneficial towards causal representation learning. A (relational) spatio-temporal knowledge base could provide a foundation upon which machine learning models could generalise, and exploring this direction from various perspectives is the main theme of this workshop. • Dr. Zhiguo Long, Southwest Jiaotong University, Chengdu, China • Dr. Jae Hee Lee, University of Hamburg, Germany Program Committee Members • Alexia Toumpa, University of Leeds, United Kingdom • Bettina Finzel, University of Bamberg, Germany • Michael Sioutis, LIRMM UMR 5506, University of Montpellier & CNRS,
France (co-chair)
With respect to organising and attending the 2nd International Workshop on Spatio-Temporal Reasoning and Learning, Michael Sioutis would like to acknowledge partial funding by the Agence Nationale de la Recherche (ANR) for the “Hybrid AI” project that is tied to his Junior Professorship Chair, and the I-SITE program of excellence of the University of Montpellier that complements the ANR funding.