Preface


   The 3rd International Workshop on Spatio-Temporal Reasoning and Learn-
ing (STRL 2024) was organised as part of the 33nd International Joint Confer-
ence on Artificial Intelligence (IJCAI 2024), the premier AI Research conference
bringing together the international AI community to communicate the advances
and achievements of AI research. IJCAI 2024 was held at Jeju island, South
Korea, and the STRL 2024 workshop was held there as a full-day event.


Context
Opposing the false dilemma of logical reasoning vs machine learning, we argue
for a synergy between these two paradigms in order to obtain hybrid AI systems
that will be robust, generalizable, and transferable. Indeed, it is well-known
that machine learning only includes statistical information and, therefore, is
not inherently able to capture perturbations (interventions or changes in the
environment), or perform 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 already given. It is becoming ever more evident in the literature that
modular AI architectures should be prioritized, 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 calculi associated with the spatial and temporal
reasoning community, be it qualitative or quantitative, naturally build upon
physics and human cognition, and could therefore form a module that would be
beneficial towards causal representation learning. A (symbolic) spatio-temporal
knowledge base could provide a dependable causal seed upon which machine
learning models could generalize, and exploring this direction from various per-
spectives is the main theme here.


Organizing Committee Members
   • Prof. Parisa Kordjamshidi, Michigan State University, US
   • Dr. Jae Hee Lee, University of Hamburg, Germany



                                        1
 • Prof. Mehul Bhatt, Örebro University, Sweden
 • Dr. Michael Sioutis, LIRMM UMR 5506, University of Montpellier &
   CNRS, France (primary contact)
 • Dr. Zhiguo Long, Southwest Jiaotong University, Chengdu, China


Program Committee Members
 • Eleni Tsalapati, National and Kapodistrian University of Athens, Greece
 • Isabelle Bloch, Sorbonne University & Télécom Paris, France
 • Kazuko Takahashi, Kwansei Gakuin University, Nishinomiya, Japan

 • Kang Liu, Shenzhen Institute of Advanced Technology, Chinese Academy
   of Sciences, China
 • Ling Cai, ByteDance Inc.
 • Parisa Kordjamshidi, Michigan State University, US (co-chair)

 • Shuang Li, The Chinese University of Hong Kong, Shenzhen, China
 • Sook-Ling Chua, Multimedia University, Cyberjaya, Malaysia
 • Yuan Yuan, Tsinghua University, Beijing, China
 • Anthony (Tony) G Cohn, University of Leeds, UK

 • Chaogui Kang, China University of Geosciences, Wuhan, China
 • Costas Mavromatis, University of Minnesota, US
 • Fan Zhang, Peking University, China

 • Jacob Suchan, Constructor University, Bremen, Germany
 • Jae Hee Lee, University of Hamburg, Germany (co-chair)
 • Jie Feng, Tsinghua University, Beijing, China
 • Joongheon Kim, Korea University, Seoul, South Korea

 • Lingbo Liu, Pengcheng Laboratory, Shenzhen, China
 • Matteo Zavatteri, University of Padua, Italy
 • Mehul Bhatt, Örebro University, Sweden (co-chair)
 • Michael Sioutis, University of Montpellier, France (co-chair)

 • Nassim Belmecheri, Simula Research Laboratory, Oslo, Norway
 • Renhe Jiang, University of Tokyo, Japan
 • Rui Zhu, University of Bristol, UK


                                    2
   • Seppe vanden Broucke, University of Ghent & KU Leuven, Belgium
   • Shufeng Kong, Sun Yat-sen University, Guangdong, China

   • Shyamanta M. Hazarika, Indian Institute of Technology Guwahati, India
   • Tianrui Li, Southwest Jiaotong University, Chengdu, China
   • Youcef Djenouri, University of South-Eastern Norway, Norway

   • Yun Jang, Sejong University, Seoul, South Korea
   • Weiming Huang, Nanyang Technological University, Singapore
   • Zhiguo Long, Southwest Jiaotong University, Chengdu, China (co-chair)
   • Zied Bouraoui, Artois University, Arras, France

   • Zongmin Ma, Nanjing University of Aeronautics and Astronautics, China


Acknowledgements
With respect to organising and attending the 3rd International Workshop on
Spatio-Temporal Reasoning and Learning, Michael Sioutis would like to ac-
knowledge 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.




                                      3