Showing 1–7 of 7 results for author: Glauer, M

ChemLog: Making MSOL Viable for Ontological Classification and Learning

Authors: Simon Flügel, Martin Glauer, Till Mossakowski, Fabian Neuhaus

Abstract: Despite its prevalence, in many domains, OWL is not expressive enough to define ontology classes. In this paper, we present an approach that allows to use monadic second-order formalisations for ontology classification. As a case study, we have applied our approach to 14 peptide-related classes from the chemistry ontology ChEBI. For these classes, a monadic second-order logic formalisation has bee… ▽ More Despite its prevalence, in many domains, OWL is not expressive enough to define ontology classes. In this paper, we present an approach that allows to use monadic second-order formalisations for ontology classification. As a case study, we have applied our approach to 14 peptide-related classes from the chemistry ontology ChEBI. For these classes, a monadic second-order logic formalisation has been developed and applied both to ChEBI as well as to 119 million molecules from the chemistry database PubChem. While this logical approach alone is limited to classification for the specified classes (in our case, (sub)classes of peptides), transformer deep learning models scale classification to the whole of the ChEBI ontology. We show that when using the classifications obtained by the logical approach as training data, the performance of the deep learning models can be significantly enhanced. △ Less

Submitted 15 September, 2025; v1 submitted 18 July, 2025; originally announced July 2025.

A fuzzy loss for ontology classification

Authors: Simon Flügel, Martin Glauer, Till Mossakowski, Fabian Neuhaus

Abstract: Deep learning models are often unaware of the inherent constraints of the task they are applied to. However, many downstream tasks require logical consistency. For ontology classification tasks, such constraints include subsumption and disjointness relations between classes. In order to increase the consistency of deep learning models, we propose a fuzzy loss that combines label-based loss with… ▽ More Deep learning models are often unaware of the inherent constraints of the task they are applied to. However, many downstream tasks require logical consistency. For ontology classification tasks, such constraints include subsumption and disjointness relations between classes. In order to increase the consistency of deep learning models, we propose a fuzzy loss that combines label-based loss with terms penalising subsumption- or disjointness-violations. Our evaluation on the ChEBI ontology shows that the fuzzy loss is able to decrease the number of consistency violations by several orders of magnitude without decreasing the classification performance. In addition, we use the fuzzy loss for unsupervised learning. We show that this can further improve consistency on data from a △ Less

Submitted 19 August, 2024; v1 submitted 3 May, 2024; originally announced May 2024.

Ontology Pre-training for Poison Prediction

Authors: Martin Glauer, Fabian Neuhaus, Till Mossakowski, Janna Hastings

Abstract: Integrating human knowledge into neural networks has the potential to improve their robustness and interpretability. We have developed a novel approach to integrate knowledge from ontologies into the structure of a Transformer network which we call ontology pre-training: we train the network to predict membership in ontology classes as a way to embed the structure of the ontology into the network,… ▽ More Integrating human knowledge into neural networks has the potential to improve their robustness and interpretability. We have developed a novel approach to integrate knowledge from ontologies into the structure of a Transformer network which we call ontology pre-training: we train the network to predict membership in ontology classes as a way to embed the structure of the ontology into the network, and subsequently fine-tune the network for the particular prediction task. We apply this approach to a case study in predicting the potential toxicity of a small molecule based on its molecular structure, a challenging task for machine learning in life sciences chemistry. Our approach improves on the state of the art, and moreover has several additional benefits. First, we are able to show that the model learns to focus attention on more meaningful chemical groups when making predictions with ontology pre-training than without, paving a path towards greater robustness and interpretability. Second, the training time is reduced after ontology pre-training, indicating that the model is better placed to learn what matters for toxicity prediction with the ontology pre-training than without. This strategy has general applicability as a neuro-symbolic approach to embed meaningful semantics into neural networks. △ Less

Submitted 20 January, 2023; originally announced January 2023.

When one Logic is Not Enough: Integrating First-order Annotations in OWL Ontologies

Authors: Simon Flügel, Martin Glauer, Fabian Neuhaus, Janna Hastings

Abstract: In ontology development, there is a gap between domain ontologies which mostly use the web ontology language, OWL, and foundational ontologies written in first-order logic, FOL. To bridge this gap, we present Gavel, a tool that supports the development of heterogeneous 'FOWL' ontologies that extend OWL with FOL annotations, and is able to reason over the combined set of axioms. Since FOL annotatio… ▽ More In ontology development, there is a gap between domain ontologies which mostly use the web ontology language, OWL, and foundational ontologies written in first-order logic, FOL. To bridge this gap, we present Gavel, a tool that supports the development of heterogeneous 'FOWL' ontologies that extend OWL with FOL annotations, and is able to reason over the combined set of axioms. Since FOL annotations are stored in OWL annotations, FOWL ontologies remain compatible with the existing OWL infrastructure. We show that for the OWL domain ontology OBI, the stronger integration with its FOL top-level ontology BFO via our approach enables us to detect several inconsistencies. Furthermore, existing OWL ontologies can benefit from FOL annotations. We illustrate this with FOWL ontologies containing mereotopological axioms that enable new meaningful inferences. Finally, we show that even for large domain ontologies such as ChEBI, automatic reasoning with FOL annotations can be used to detect previously unnoticed errors in the classification. △ Less

Submitted 7 October, 2022; originally announced October 2022.

ESC-Rules: Explainable, Semantically Constrained Rule Sets

Authors: Martin Glauer, Robert West, Susan Michie, Janna Hastings

Abstract: We describe a novel approach to explainable prediction of a continuous variable based on learning fuzzy weighted rules. Our model trains a set of weighted rules to maximise prediction accuracy and minimise an ontology-based 'semantic loss' function including user-specified constraints on the rules that should be learned in order to maximise the explainability of the resulting rule set from a user… ▽ More We describe a novel approach to explainable prediction of a continuous variable based on learning fuzzy weighted rules. Our model trains a set of weighted rules to maximise prediction accuracy and minimise an ontology-based 'semantic loss' function including user-specified constraints on the rules that should be learned in order to maximise the explainability of the resulting rule set from a user perspective. This system fuses quantitative sub-symbolic learning with symbolic learning and constraints based on domain knowledge. We illustrate our system on a case study in predicting the outcomes of behavioural interventions for smoking cessation, and show that it outperforms other interpretable approaches, achieving performance close to that of a deep learning model, while offering transparent explainability that is an essential requirement for decision-makers in the health domain. △ Less

Submitted 26 August, 2022; originally announced August 2022.

Automated and Explainable Ontology Extension Based on Deep Learning: A Case Study in the Chemical Domain

Authors: Adel Memariani, Martin Glauer, Fabian Neuhaus, Till Mossakowski, Janna Hastings

Abstract: Reference ontologies provide a shared vocabulary and knowledge resource for their domain. Manual construction enables them to maintain a high quality, allowing them to be widely accepted across their community. However, the manual development process does not scale for large domains. We present a new methodology for automatic ontology extension and apply it to the ChEBI ontology, a prominent refer… ▽ More Reference ontologies provide a shared vocabulary and knowledge resource for their domain. Manual construction enables them to maintain a high quality, allowing them to be widely accepted across their community. However, the manual development process does not scale for large domains. We present a new methodology for automatic ontology extension and apply it to the ChEBI ontology, a prominent reference ontology for life sciences chemistry. We trained a Transformer-based deep learning model on the leaf node structures from the ChEBI ontology and the classes to which they belong. The model is then capable of automatically classifying previously unseen chemical structures. The proposed model achieved an overall F1 score of 0.80, an improvement of 6 percentage points over our previous results on the same dataset. Additionally, we demonstrate how visualizing the model's attention weights can help to explain the results by providing insight into how the model made its decisions. △ Less

Submitted 19 September, 2021; originally announced September 2021.

An Institution for Simple UML State Machines

Authors: Alexander Knapp, Till Mossakowski, Markus Roggenbach, Martin Glauer

Abstract: We present an institution for UML state machines without hierarchical states. The interaction with UML class diagrams is handled via institutions for guards and actions, which provide dynamic components of states (such as valuations of attributes) but abstract away from details of class diagrams. We also study a notion of interleaving product, which captures the interaction of several state machin… ▽ More We present an institution for UML state machines without hierarchical states. The interaction with UML class diagrams is handled via institutions for guards and actions, which provide dynamic components of states (such as valuations of attributes) but abstract away from details of class diagrams. We also study a notion of interleaving product, which captures the interaction of several state machines. The interleaving product construction is the basis for a semantics of composite structure diagrams, which can be used to specify the interaction of state machines. This work is part of a larger effort to build a framework for formal software development with UML, based on a heterogeneous approach using institutions. △ Less

Submitted 17 November, 2014; originally announced November 2014.

Comments: 24 pages. arXiv admin note: substantial text overlap with arXiv:1403.7747