Combining Inductive and Deductive Reasoning for Query Answering over Incomplete Knowledge Graphs

Medina Andresel (Speaker), , , ,

Research output: Chapter in Book or Conference ProceedingsConference Proceedings with Oral Presentationpeer-review

Abstract

Current methods for embedding-based query answering over incomplete Knowledge Graphs (KGs) only focus on inductive reasoning, i.e., predicting answers by learning patterns from the data, and lack the complementary ability to do deductive reasoning, which requires the application of domain knowledge to infer further information. To address this shortcoming, we investigate the problem of incorporating ontologies into embedding-based query answering models by defining the task of embedding-based ontology-mediated query answering. We propose various integration strategies into prominent representatives of embedding models that involve (1) different ontology-driven data augmentation techniques and (2) adaptation of the loss function to enforce the ontology axioms. We design novel benchmarks for the considered task based on the LUBM and the NELL KGs and evaluate our methods on them. The achieved improvements in the setting that requires both inductive and deductive reasoning are from 20% to 55% in HITS@3.
Original languageEnglish
Title of host publicationProceedings of the 32nd ACM International Conference on Information & Knowledge Management
Subtitle of host publicationCIKM '23
PublisherAssociation for Computing Machinery (ACM)
Pages15–24
Number of pages10
ISBN (Print)979-8-4007-0124-5
DOIs
Publication statusPublished - 21 Oct 2023
EventCIKM '23: The 32nd ACM International Conference on Information and Knowledge Management - Birmingham , United Kingdom , Birmingham , United Kingdom
Duration: 21 Oct 202325 Oct 2023

Conference

ConferenceCIKM '23: The 32nd ACM International Conference on Information and Knowledge Management
Country/TerritoryUnited Kingdom
CityBirmingham
Period21/10/2325/10/23

Research Field

  • Former Research Field - Data Science

Keywords

  • ontologies
  • knowledge graphs
  • query answering
  • embedding models
  • neuro-symbolic QA

Fingerprint

Dive into the research topics of 'Combining Inductive and Deductive Reasoning for Query Answering over Incomplete Knowledge Graphs'. Together they form a unique fingerprint.

Cite this