Skip to content

news

Our survey paper on Neurosymbolic AI for reasoning over knowledge graphs has just been published in TNNLS

    Abstract:

    Neurosymbolic artificial intelligence (AI) is an increasingly active area of research that combines symbolic reasoning methods with deep learning to leverage their complementary benefits. As knowledge graphs (KGs) are becoming a popular way to represent heterogeneous and multirelational 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 to generate models that facilitate interpretability, maintain competitive performance, and integrate expert knowledge. Therefore, we survey methods that perform neurosymbolic reasoning tasks on KGs and 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 unique characteristics and limitations of these methods and then propose several prospective directions toward which this field of research could evolve.

    L. N. DeLong, R. F. Mir and J. D. Fleuriot, “Neurosymbolic AI for Reasoning Over Knowledge Graphs: A Survey,” in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2024.3420218.

    keywords: {Cognition;Artificial intelligence;Artificial neural networks;Surveys;Taxonomy;Knowledge graphs;Semantics;Graph neural networks (GNNs);hybrid artificial intelligence (AI);knowledge graphs (KGs);neurosymbolic AI;representation learning},

    Our paper “Linear Resources in Isabelle/HOL” has just been published in the Journal of Automated Reasoning

      Abstract:

      We present a formal framework for process composition based on actions that are specified by their input and output resources. The correctness of these compositions is verified by translating them into deductions in intuitionistic linear logic. As part of the verification we derive simple conditions on the compositions which ensure well-formedness of the corresponding deduction when satisfied. We mechanise the whole framework, including a deep embedding of ILL, in the proof assistant Isabelle/HOL. Beyond the increased confidence in our proofs, this allows us to automatically generate executable code for our verified definitions. We demonstrate our approach by formalising part of the simulation game Factorio and modelling a manufacturing process in it. Our framework guarantees that this model is free of bottlenecks.

      Smola, F., Fleuriot, J.D. Linear Resources in Isabelle/HOL. J Autom Reasoning 68, 9 (2024). https://doi.org/10.1007/s10817-024-09698-2

      Opportunity: Fully funded PhD in predicting harm from prescribed drugs

        Fully Funded PhD in Predicting harm from prescribed drugs in people with polypharmacy, multimorbidity and frailty.

        The aim of this project is to develop and validate new models to predict who is at risk of being harmed by prescribed drugs, focusing on the outcome of acute kidney injury. More information available here.

        Fiona Smith’s exhibition “The BOX” premieres at the Edinburgh Science Festival!

          We are proud to announce that AI Modelling Lab PhD Student Fiona Smith’s exhibition “The BOX” is running from the 6th to the 19th of April 2024 as part of the Edinburgh Science Festival. Fiona is funded by our Centre for Doctoral Traning in Biomedical AI and was selected to be the Creator in Residence at Fraunhofer MEVIS.

          The live exhibition can be visited at Inspace, Crichton St, University of Edinburgh.

           

           

          Jorge Gaete Villegas passes his PhD viva

            Congratulations to Jorge Gatete Villegas who succesfully defended his thesis on Modelling and Predicting Medical Outcomes for Intensive Care Patients via Network Mechanisms and Machine
            Learning
            . His examiners were Dr Areti Manataki of the University of St Andrews and Dr Sohan Seth of the University of Edinburgh.

            Special Issue on Mathematics in Artificial Intelligence

              Paola Galdi and Jacques Fleuriot are editing a special issue of the journal Mathematics in Computer Science focused on the interplay between mathematics and AI. The Call for Papers can be found here. The submission deadline is on the 31st of January 2024.

               

              Paper on conformance checking over probabilistic events accepted at HICSS-57

                The paper on “Alignment-based conformance checking over probabilistic events” by Jiawei Zheng, Petros Papapanagiotou and Jacques Fleuriot has been accepted at the Hawaii International Conference on System Sciences (HICSS-57).

                Abstract:

                Conformance checking techniques allow us to evaluate how well some exhibited behaviour, represented by a trace of monitored events, conforms to a specified process model. Modern monitoring and activity recognition technologies, such as those relying on sensors, the IoT, statistics and AI, can produce a wealth of relevant event data. However, this data is typically characterised by noise and uncertainty, in contrast to the assumption of a deterministic event log required by conformance checking algorithms. In this paper, we extend alignment-based conformance checking to function under a probabilistic event log.

                We introduce a weighted trace model and weighted alignment cost function, and a custom threshold parameter that controls the level of confidence on the event data vs. the process model. The resulting algorithm considers activities of lower but sufficiently high probability that better align with the process model. We explain the algorithm and its motivation both from formal and intuitive perspectives, and demonstrate its functionality in comparison with deterministic alignment using real-life datasets.

                Keywords: Conformance checking, Probabilistic events, Uncertainty, Probabilistic cost function

                Pre-print on Associations between Morbidities in Small But Important Subgroup using a Bayesian approach

                  Our paper on the “Associations between Morbidities in Small But Important Subgroups: A Novel Bayesian Approach for Robust Multimorbidity Analysis with Small Sample Sizes”  is out.

                  Abstract:

                  Background: Robustly examining associations between long-term conditions may be important in identifying opportunities for intervention in multimorbidity but is challenging when data is limited. We have developed a Bayesian inference framework that is robust to sparse data and have used it to quantify morbidity associations in the oldest old, a population with limited available data.

                  Methods: We conducted a retrospective cross-sectional cohort study of a representative dataset of primary care patients in Scotland. We included 40 long-term conditions and studied their associations in 12,009 individuals aged 90 and older, stratified by sex, to study the effect of small sample sizes in the estimation of associations between long-term conditions. We analysed associations obtained with Relative Risk (RR), a standard measure in the literature, and compared them with a new measure of associations, Associations Beyond Chance (ABC), that utilises a Bayesian framework. To enable a broad exploration of interactions between long-term conditions, we built networks of association and assessed differences in their analysis when associations are estimated by RR or ABC.

                  Findings: Our Bayesian framework was appropriately more cautious in attributing association when evidence is small, as it dismissed six of the top ten associations reported by RR, most of which relate to uncommon conditions. This caution in reporting association was also present in reporting differences in associations between sex, for which ABC only reported as significant about one-fifth of those reported by RR. Last, the presence of potentially inaccurate associations by RR also affected the aggregated measures of multimorbidity and network representations.

                  Interpretation: Incorporating uncertainty into multimorbidity research is crucial to avoid misleading findings when data is limited, a problem that particularly affects small but important subgroups. Our proposed framework improves the reliability of estimations of associations and, more in general, of research into disease mechanisms and multimorbidity.

                  More information at SSRN: https://ssrn.com/abstract=4515875 or http://dx.doi.org/10.2139/ssrn.4515875.