Multi-hop path queries over knowledge graphs with neural memory networks

Qinyong Wang, Hongzhi Yin, Weiqing Wang, Zi Huang, Guibing Guo, Quoc Viet Hung Nguyen

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

3 Citations (Scopus)

Abstract

There has been increasing research interest in inferring missing information from existing knowledge graphs (KGs) due to the emergence of a wide range of knowledge graph downstream applications such as question answering systems and search engines. Reasoning over knowledge graphs, which queries the correct entities only through a path consisting of multiple consecutive relations/hops from the starting entity, is an effective approach to do this task, but this topic has been rarely studied. As an attempt, the compositional training method equally treats the constructed multi-hop paths and one-hop relations to build training data, and then trains conventional knowledge graph completion models such as TransE in a compositional manner on the training data. However, it does not incorporate additional information along the paths during training, such as the intermediate entities and their types, which can be helpful to guide the reasoning towards the correct destination answers. Moreover, compositional training can only extend some existing models that can be composable, which significantly limits its applicability. Therefore, we design a novel model based on the recently proposed neural memory networks, which have large external memories and flexible writing/reading schemes, to address these problems. Specifically, we first introduce a single network layer, which is then used as the building block for a multi-layer neural network called TravNM, and a flexible memory updating method is developed to facilitate writing intermediate entity information during the multi-hop reasoning into memories. Finally, we conducted extensive experiments on large datasets, and the experimental results show the superiority of our proposed TravNM for reasoning over knowledge graphs with multiple hops.

Original languageEnglish
Title of host publicationDatabase Systems for Advanced Applications
Subtitle of host publication24th International Conference, DASFAA 2019 Chiang Mai, Thailand, April 22–25, 2019 Proceedings, Part I
EditorsGuoliang Li, Jun Yang, Joao Gama, Juggapong Natwichai, Yongxin Tong
Place of PublicationCham Switzerland
PublisherSpringer
Pages777-794
Number of pages18
ISBN (Electronic)9783030185763
ISBN (Print)9783030185756
DOIs
Publication statusPublished - 2019
EventDatabase Systems for Advanced Applications 2019 - Chiang Mai, Thailand
Duration: 22 Apr 201925 Apr 2019
Conference number: 24th
https://dasfaa2019.eng.cmu.ac.th/
https://link.springer.com/book/10.1007/978-3-030-18576-3 (Proceedings)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11446
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceDatabase Systems for Advanced Applications 2019
Abbreviated titleDASFAA 2019
CountryThailand
CityChiang Mai
Period22/04/1925/04/19
Internet address

Cite this