8 papers
Soft Ontology Priors over Latent Concept Posteriors for Weakly Supervised Neuro-Symbolic Learning
Tengwei Song, Robert Hoehndorf
Neuro-symbolic (NeSy) predictors that supervise only the task label suffer from reasoning shortcuts: distinct concept mappings achieve the same maximum likelihood, leaving the reco…
MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments
Tengwei Song, Robert Hoehndorf
LLM agents are flexible in language interaction, but using them as long-horizon planners is costly and prone to hallucinated or invalid actions. This paper targets a different role…
A hierarchy of faithfulness criteria for knowledge base completion
Olga Mashkova, Robert Hoehndorf
Knowledge graph completion is evaluated by ranking observed triples above randomly corrupted ones, which treats every unobserved fact as false. When the object being completed is a…
Neuro-symbolic learning over OWL 2 DL via consequence-based compilation to differentiable circuits
Olga Mashkova, Asaad Mohammedsaleh, Fernando Zhapa-Camacho +1
OWL 2 DL ontologies, grounded in the description logic , express large knowledge bases in biomedicine and the Semantic Web. Neuro-symbolic (NeSy) learners over des…
Moose: Latent concept learning with reasoning-shortcut awareness in
Olga Mashkova, Asaad Mohammedsaleh, Fernando Zhapa-Camacho +1
The OWL 2 EL profile is used in some of the largest production ontologies, including the Gene Ontology and SNOMED CT. Existing neuro-symbolic (NeSy) learning methods accept proposi…
INDIGENA: inductive prediction of disease-gene associations using phenotype ontologies
Fernando Zhapa-Camacho, Robert Hoehndorf
Motivation: Predicting gene-disease associations (GDAs) is the problem to determine which gene is associated with a disease. GDA prediction can be framed as a ranking problem where…
Fully Geometric Multi-Hop Reasoning on Knowledge Graphs with Transitive Relations
Fernando Zhapa-Camacho, Robert Hoehndorf
Multi-hop logical reasoning on knowledge graphs requires faithfully mapping the logical semantics to latent space. Current geometric embedding methods show to be useful on this tas…
Large-Scale Knowledge Integration for Enhanced Molecular Property Prediction
Yasir Ghunaim, Robert Hoehndorf
Pre-training machine learning models on molecular properties has proven effective for generating robust and generalizable representations, which is critical for advancements in dru…