STRL 2022 : 1st International Workshop on Spatio-Temporal Reasoning and Learning

The First International Workshop on Spatio-Temporal Reasoning and Learning (STRL), collocated with IJCAI-ECAI 2022 (https://ijcai-22.org/)

Website: https://strl2022.github.io/


Introduction
========

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. As an example, in the on-going IJCAI Angry Birds competitions (http://aibirds.org/angry-birds-ai-competition.html), machine learning models generally struggle to achieve good performance, because there is no sufficient encoding of spatial and temporal structure and relations; shooting a bird with a given trajectory can clearly have some very well determined effect (based on the laws of physics), which could in turn cause a chain of effects to occur, but machine learning models are not able to capture this behavior, for the reasons mentioned earlier. 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 perspectives is the main theme of this workshop.


Topics
====

In this workshop, we invite the research community in artificial intelligence to submit works related to the proposed integration of spatial and temporal reasoning with machine learning, revolving around the following topic areas:

Real-world problems / applications of spatio-temporal reasoning and learning

Challenges in spatio-temporal reasoning and learning

Neuro-symbolic approaches for spatio-temporal reasoning and learning

Probabilistic world models for spatio-temporal reasoning and learning

Probabilistic inference for spatio-temporal reasoning and learning

Datasets for spatio-temporal reasoning and learning

Metrics for assessing spatio-temporal reasoning and learning methods

Limitations in machine learning for spatio-temporal reasoning and learning; how far can machine learning go?

Relation between causal reasoning and spatial and temporal reasoning

The list above is by no means exhaustive, as the aim is to foster the debate around all aspects of the suggested integration.


Submission
=======
Guidelines
..............

Papers should be formatted according to the IJCAI-ECAI 2022 formatting guidelines and submitted as a single PDF file. We welcome submissions across the full spectrum of theoretical and practical work including research ideas, methods, tools, simulations, applications or demos, practical evaluations, and surveys. Submissions that are 2 pages long (excluding references and appendices) will be considered for a poster, and submissions that are at least 4 pages and up to 6 pages long (excluding references and appendices) will be considered for an oral presentation. All papers will be peer-reviewed in a single-blind process and assessed based on their novelty, technical quality, potential impact, clarity, and reproducibility (when applicable). Workshop submissions and camera-ready versions will be handled by EasyChair; the submission link is as follows: https://easychair.org/conferences/?conf=strl2022

Important Dates
.......................................

May 20, 2022: Workshop Paper Due Date

June 3, 2022: Notification of Paper Acceptance

June 17, 2022: Camera-ready papers due

Note: all deadlines are AoE (Anywhere on Earth).


Proceedings
========

The accepted papers will appear on the workshop website. We also intend to publish the workshop proceedings with CEUR-WS.org; this option will be discussed with the authors of accepted papers and is subject to the CEUR-WS.org preconditions. We note that, as STRL 2022 is a workshop, not a conference, submission of the same paper to conferences or journals is acceptable from our standpoint.


Organizing Committee
==============

Dr. Michael Sioutis, Bamberg University, Germany

Dr. Zhiguo Long, Southwest Jiaotong University, Chengdu, China

Dr. John Stell, Leeds University, UK

Prof. Jochen Renz, Australian National University, Australia


Contact
=====

All questions about submissions should be emailed to strl2022 at easychair.org