[DL] [CFP] First International Workshop on Logical Foundations of Neuro-Symbolic AI (LNSAI 2024)

[Marco Console]

******************************************************************************


        LNSAI-2024: First International Workshop on Logical Foundations of
Neuro-Symbolic AI (LNSAI 2024)
                   -- co-located with IJCAI 2024  --

                      August 5, 2024, Jeju Island, South Korea

        Web site: https://sites.google.com/view/lnsai2024/
        Submission link:
https://openreview.net/group?id=ijcai.org/IJCAI/2024/Workshop/LNSAI
        Abstract registration deadline: May 8, 2024 (AoE)
        Submission deadline: May 15, 2024 (AoE)
        Paper Acceptance Notification: June 3, 2024 (AoE)
        Camera-ready Deadline: July 28, 2024 (AoE)
        Workshop Date: August 5, 2024
        Contact Email: cima at diag.uniroma1.it

******************************************************************************

Deductive and Inductive Reasoning are the two pillars of Artificial
Intelligence (AI) systems that deal with data. Deductive Reasoning
techniques are based on symbolic manipulation of information and
usually infer new knowledge using automated logic-based procedures. On
the contrary, Inductive Reasoning techniques learn patterns often
using sub-symbolic representations such as Artificial Neural
Networks. Using these representations, the former can derive accurate
and explainable knowledge but are susceptible to noisy data, whereas
the latter are robust to data diversity but generate predictions that
can be potentially imprecise and generally opaque. Due to these
characteristics, deductive and inductive reasoning techniques excel at
solving and struggle with completely different, and often
complementary, families of problems.

As a result, we are currently experiencing a new era of AI where
symbolic and neural techniques are being combined to leverage the best
from both of them. It is therefore extremely important that such
promising synergy is accurately formalized at its core, and more
specifically grounded on formal methods, based on some form of logic.

Topics of Interest
---------------------------------------------

The LNSAI workshop welcomes new papers or summaries of recently
published papers that combine deductive and inductive reasoning by
means of logical approaches (taken in the broadest sense), and more
generally revolving around the following topic areas:

    - Formal Aspects of the Integration between Symbolic and Neural
Approaches
    - Neuro-Symbolic Methods for Reasoning and Learning
    - Philosophical Aspects of Neuro-Symbolic AI
    - Historical Perspectives of Neuro-Symbolic AI
    - Semantic Web and Deep Learning
    - Neuro-Symbolic Reinforcement Learning
    - Neuro-Symbolic Description Logic Reasoners
    - Combine Deductive and Inductive Reasoning for FAIR Data Management
    - Question Answering exploiting Knowledge Graphs and Deep Learning
    - Temporal Knowledge Graph Embeddings
    - The Role of Description Logic Ontologies in Knowledge Graph Embeddings
    - Inductive Logic Programming
    - Logical Methods for Quality Assessment
    - Analyzing the Expressive Power of Graph Neural Networks
    - Logic-based Explanations for Machine Learning Predictions
    - Knowledge Representation and Reasoning using Deep Neural Networks

Submission Details
---------------------------------------------

We welcome three types of submissions:

    - Regular long papers of up to 12 pages (including figures,
acknowledgments, and references)
    - Short/Position papers of up to 5 pages (including figures,
acknowledgments, and references)
    - Extended abstracts of up to 4 pages (including figures,
acknowledgments, and references)


All submissions must be written in English, and formatted
according to the 1-column CEURART style (which can be found also
in Overleaf here). Supplementary material can be added as an
appendix at the end of the main PDF file, i.e. you can submit a
single PDF file containing the main body of the paper followed by
an appendix which will not be included in the page count.

The reviewing process will be single-blind and therefore
submissions should not be anonymized. Authors can submit papers
through OpenReview using the link above.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.zih.tu-dresden.de/pipermail/dl/attachments/20240408/ebaa6e45/attachment-0001.htm>