LinE: Logical Query Reasoning over Hierarchical Knowledge Graphs

Zijian Huang, Meng Fen Chiang, Wang Chien Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Scopus citations

Abstract

Logical reasoning over Knowledge Graphs (KGs) for first-order logic (FOL) queries performs the query inference over KGs with logical operators, including conjunction, disjunction, existential quantification and negation, to approximate true answers in embedding spaces. However, most existing work imposes strong distributional assumptions (e.g., Beta distribution) to represent entities and queries into presumed distributional shape, which limits their expressive power. Moreover, query embeddings are challenging due to the relational complexities in multi-relational KGs (e.g., symmetry, anti-symmetry and transitivity). To bridge the gap, we propose a logical query reasoning framework, Line Embedding (LinE), for FOL queries. To relax the distributional assumptions, we introduce the logic space transformation layer, which is a generic neural function that converts embeddings from probabilistic distribution space to LinE embeddings space. To tackle multi-relational and logical complexities, we formulate neural relation-specific projections and individual logical operators to truthfully ground LinE query embeddings on logical regularities and KG factoids. Lastly, to verify the LinE embedding quality, we generate a FOL query dataset from WordNet, which richly encompasses hierarchical relations. Extensive experiments show superior reasoning sensitivity of LinE on three benchmarks against strong baselines, particularly for multi-hop relational queries and negation-related queries.

Original languageEnglish (US)
Title of host publicationKDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages615-625
Number of pages11
ISBN (Electronic)9781450393850
DOIs
StatePublished - Aug 14 2022
Event28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 - Washington, United States
Duration: Aug 14 2022Aug 18 2022

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022
Country/TerritoryUnited States
CityWashington
Period8/14/228/18/22

All Science Journal Classification (ASJC) codes

  • Software
  • Information Systems

Fingerprint

Dive into the research topics of 'LinE: Logical Query Reasoning over Hierarchical Knowledge Graphs'. Together they form a unique fingerprint.

Cite this