Relevance search over schema-rich knowledge graphs

Yu Gu, Ziyang Li, Tianshuo Zhou, Jeff Z. Pan, Gong Cheng, Yuzhong Qu

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

Abstract

Relevance search over a knowledge graph (KG) has gained much research attention. Given a query entity in a KG, the problem is to find its most relevant entities. However, the relevance function is hidden and dynamic. Different users for different queries may consider relevance from different angles of semantics. The ambiguity in a query is more noticeable in the presence of thousands of types of entities and relations in a schema-rich KG, which has challenged the effectiveness and scalability of existing methods. To meet the challenge, our approach called RelSUE requests a user to provide a small number of answer entities as examples, and then automatically learns the most likely relevance function from these examples. Specifically, we assume the intent of a query can be characterized by a set of meta-paths at the schema level. RelSUE searches a KG for diversified significant meta-paths that best characterize the relevance of the user-provided examples to the query entity. It reduces the large search space of a schema-rich KG using distance and degree-based heuristics, and performs reasoning to deduplicate meta-paths that represent equivalent query-specific semantics. Finally, a linear model is learned to predict meta-path based relevance. Extensive experiments demonstrate that RelSUE outperforms several state-of-the-art methods.

Original languageEnglish
Title of host publicationWSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining
PublisherAssociation for Computing Machinery, Inc
Pages114-122
Number of pages9
ISBN (Electronic)9781450359405
DOIs
Publication statusPublished - 30 Jan 2019
Event12th ACM International Conference on Web Search and Data Mining, WSDM 2019 - Melbourne, Australia
Duration: 11 Feb 201915 Feb 2019

Conference

Conference12th ACM International Conference on Web Search and Data Mining, WSDM 2019
CountryAustralia
CityMelbourne
Period11/02/1915/02/19

Fingerprint

Semantics
Scalability
Experiments

Keywords

  • Knowledge graph
  • Meta-path
  • Reasoning
  • Relevance search

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software
  • Computer Science Applications

Cite this

Gu, Y., Li, Z., Zhou, T., Pan, J. Z., Cheng, G., & Qu, Y. (2019). Relevance search over schema-rich knowledge graphs. In WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining (pp. 114-122). Association for Computing Machinery, Inc. https://doi.org/10.1145/3289600.3290970

Relevance search over schema-rich knowledge graphs. / Gu, Yu; Li, Ziyang; Zhou, Tianshuo; Pan, Jeff Z.; Cheng, Gong; Qu, Yuzhong.

WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc, 2019. p. 114-122.

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

Gu, Y, Li, Z, Zhou, T, Pan, JZ, Cheng, G & Qu, Y 2019, Relevance search over schema-rich knowledge graphs. in WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc, pp. 114-122, 12th ACM International Conference on Web Search and Data Mining, WSDM 2019, Melbourne, Australia, 11/02/19. https://doi.org/10.1145/3289600.3290970
Gu Y, Li Z, Zhou T, Pan JZ, Cheng G, Qu Y. Relevance search over schema-rich knowledge graphs. In WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc. 2019. p. 114-122 https://doi.org/10.1145/3289600.3290970
Gu, Yu ; Li, Ziyang ; Zhou, Tianshuo ; Pan, Jeff Z. ; Cheng, Gong ; Qu, Yuzhong. / Relevance search over schema-rich knowledge graphs. WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc, 2019. pp. 114-122
@inproceedings{8329973faf844aec89e4b1a1dfab7186,
title = "Relevance search over schema-rich knowledge graphs",
abstract = "Relevance search over a knowledge graph (KG) has gained much research attention. Given a query entity in a KG, the problem is to find its most relevant entities. However, the relevance function is hidden and dynamic. Different users for different queries may consider relevance from different angles of semantics. The ambiguity in a query is more noticeable in the presence of thousands of types of entities and relations in a schema-rich KG, which has challenged the effectiveness and scalability of existing methods. To meet the challenge, our approach called RelSUE requests a user to provide a small number of answer entities as examples, and then automatically learns the most likely relevance function from these examples. Specifically, we assume the intent of a query can be characterized by a set of meta-paths at the schema level. RelSUE searches a KG for diversified significant meta-paths that best characterize the relevance of the user-provided examples to the query entity. It reduces the large search space of a schema-rich KG using distance and degree-based heuristics, and performs reasoning to deduplicate meta-paths that represent equivalent query-specific semantics. Finally, a linear model is learned to predict meta-path based relevance. Extensive experiments demonstrate that RelSUE outperforms several state-of-the-art methods.",
keywords = "Knowledge graph, Meta-path, Reasoning, Relevance search",
author = "Yu Gu and Ziyang Li and Tianshuo Zhou and Pan, {Jeff Z.} and Gong Cheng and Yuzhong Qu",
year = "2019",
month = "1",
day = "30",
doi = "10.1145/3289600.3290970",
language = "English",
pages = "114--122",
booktitle = "WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Relevance search over schema-rich knowledge graphs

AU - Gu, Yu

AU - Li, Ziyang

AU - Zhou, Tianshuo

AU - Pan, Jeff Z.

AU - Cheng, Gong

AU - Qu, Yuzhong

PY - 2019/1/30

Y1 - 2019/1/30

N2 - Relevance search over a knowledge graph (KG) has gained much research attention. Given a query entity in a KG, the problem is to find its most relevant entities. However, the relevance function is hidden and dynamic. Different users for different queries may consider relevance from different angles of semantics. The ambiguity in a query is more noticeable in the presence of thousands of types of entities and relations in a schema-rich KG, which has challenged the effectiveness and scalability of existing methods. To meet the challenge, our approach called RelSUE requests a user to provide a small number of answer entities as examples, and then automatically learns the most likely relevance function from these examples. Specifically, we assume the intent of a query can be characterized by a set of meta-paths at the schema level. RelSUE searches a KG for diversified significant meta-paths that best characterize the relevance of the user-provided examples to the query entity. It reduces the large search space of a schema-rich KG using distance and degree-based heuristics, and performs reasoning to deduplicate meta-paths that represent equivalent query-specific semantics. Finally, a linear model is learned to predict meta-path based relevance. Extensive experiments demonstrate that RelSUE outperforms several state-of-the-art methods.

AB - Relevance search over a knowledge graph (KG) has gained much research attention. Given a query entity in a KG, the problem is to find its most relevant entities. However, the relevance function is hidden and dynamic. Different users for different queries may consider relevance from different angles of semantics. The ambiguity in a query is more noticeable in the presence of thousands of types of entities and relations in a schema-rich KG, which has challenged the effectiveness and scalability of existing methods. To meet the challenge, our approach called RelSUE requests a user to provide a small number of answer entities as examples, and then automatically learns the most likely relevance function from these examples. Specifically, we assume the intent of a query can be characterized by a set of meta-paths at the schema level. RelSUE searches a KG for diversified significant meta-paths that best characterize the relevance of the user-provided examples to the query entity. It reduces the large search space of a schema-rich KG using distance and degree-based heuristics, and performs reasoning to deduplicate meta-paths that represent equivalent query-specific semantics. Finally, a linear model is learned to predict meta-path based relevance. Extensive experiments demonstrate that RelSUE outperforms several state-of-the-art methods.

KW - Knowledge graph

KW - Meta-path

KW - Reasoning

KW - Relevance search

UR - http://www.scopus.com/inward/record.url?scp=85061747953&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/relevance-search-schemarich-knowledge-graphs

U2 - 10.1145/3289600.3290970

DO - 10.1145/3289600.3290970

M3 - Conference contribution

SP - 114

EP - 122

BT - WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining

PB - Association for Computing Machinery, Inc

ER -