Papers › A fuzzy loss for ontology classification

A fuzzy loss for ontology classification

3 May 2024arXiv:2405.02083archive 2025-07-28

Simon Flügel, Martin Glauer, Till Mossakowski, Fabian Neuhaus

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

PaperPDFCode

Code

cheb-ai/python-chebai officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationDeep Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Ontology

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections