Skip to content


Survey pre-print on Neurosymbolic AI for Reasoning on Graph Structures is out on arXiv

    Our article on Neurosymbolic AI for Reasoning on Graph Structure is out. This is a comprehensive survey by Lauren Nicole DeLong, Ramon Fernández Mir, Matthew Whyte, Zonglin Ji and Jacques D. Fleuriot.


    Neurosymbolic AI is an increasingly active area of research which aims to combine symbolic reasoning methods with deep learning to generate models with both high predictive performance and some degree of human-level comprehensibility. As knowledge graphs are becoming a popular way to represent heterogeneous and multi-relational data, methods for reasoning on graph structures have attempted to follow this neurosymbolic paradigm. Traditionally, such approaches have utilized either rule-based inference or generated representative numerical embeddings from which patterns could be extracted. However, several recent studies have attempted to bridge this dichotomy in ways that facilitate interpretability, maintain performance, and integrate expert knowledge. Within this article, we survey a breadth of methods that perform neurosymbolic reasoning tasks on graph structures. Within this article, we survey a breadth of methods that perform neurosymbolic reasoning tasks on graph structures. To better compare the various methods, we propose a novel taxonomy by which we can classify them. Specifically, we propose three major categories: (1) logically-informed embedding approaches, (2) embedding approaches with logical constraints, and (3) rule-learning approaches. Alongside the taxonomy, we provide a tabular overview of the approaches and links to their source code, if available, for more direct comparison. Finally, we discuss the applications on which these methods were primarily used and propose several prospective directions toward which this new field of research could evolve.

    The paper can be found on arXiv at arXiv:2302.07200 and an associated Github repository is here.

    New Project funded by the Edinburgh Laboratory for Integrated Artificial Intelligence (ELIAI)

      The Edinburgh Laboratory for Integrated Artificial Intelligence (ELIAI) will fund a new project on integrating theorem proving and neural learning led by Jacques Fleuriot in collaboration with Ram Ramamoorthy. The 2-year project will involve the development of theorem-proving framework that allows for formal representation and proofs, and then faithful code-generation, of user-specified, spatio-temporal constraints that can then be used for learning in scenarios involving human-robot interaction

      Opportunity: Multimorbidity PhD Programme for Health Professionals

        The Clinical PhD Research Fellowships are fixed term 3-year appointments offering training, mentoring and support to health professionals undertaking a PhD on the topic of multimorbidity.

        We are looking for applicants who are interested in working on understanding the “Co-existing mental and physical multimorbidity, adverse events, and longer term outcomes in hospitalised patients with sepsis“.

        More info available here.

        Paper accepted at CICM 2022

          Our paper, “Re-imagining the Isabelle Archive of Formal Proofs” (MacKenzie, Huch, Vaughan and Fleuriot), has been accepted at the 15th Conference on Intelligent Computer Mathematics (CICM 2022).

          New Archive of Formal Proof Website

            A project involving Carlin MacKenzie, James Vaughan and Jacques Fleuriot has resulted in a re-design and re-implementation of the Archive of Formal Proofs, which is a collection of proof libraries, examples, and larger scientific developments, mechanically checked in the theorem prover Isabelle. The revamped website ( is now live and will serve the Isabelle community across the world. The Edinburgh team worked with Fabian Huch of TU Munich to integrate their work into the AFP infrastructure.