Rewrite or not rewrite? ML-based algorithm selection for datalog query answering on knowledge graphs

Unmesh Joshi; Ceriel Jacobs; Jacopo Urbani

doi:10.3233/FAIA200168

Rewrite or not rewrite? ML-based algorithm selection for datalog query answering on knowledge graphs

Unmesh Joshi
, Ceriel Jacobs
, Jacopo Urbani

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Query-driven reasoning techniques with Datalog rules, like Magic Sets (MS), are ideal for implementing query answering on Knowledge Graphs (KGs). For some queries, executing a rewriting procedure like MS is the best choice, but for others a non-rewriting procedure like Query-subquery (QSQ) can be faster. Choosing beforehand which procedure should be used is not trivial and mistakes can be costly. To address this problem, we describe a first-of-its-kind method that builds a Machine Learning (ML) model to predict whether a query should be answered with MS or with QSQ. Experiments on several well-known KGs show that our method can return accurate predictions, and this leads to a significant reduction of the response time of query answering.

Original language	English
Title of host publication	ECAI 2020
Subtitle of host publication	24th European Conference on Artificial Intelligence, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020 - Proceedings
Editors	Giuseppe De Giacomo, Alejandro Catala, Bistra Dilkina, Michela Milano, Senen Barro, Alberto Bugarin, Jerome Lang
Publisher	IOS Press BV
Pages	792-799
Number of pages	8
ISBN (Electronic)	9781643681016
ISBN (Print)	9781643681009
DOIs	https://doi.org/10.3233/FAIA200168
Publication status	Published - 2020
Event	24th European Conference on Artificial Intelligence, ECAI 2020, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020 - Santiago de Compostela, Online, Spain Duration: 29 Aug 2020 → 8 Sept 2020

Publication series

Name	Frontiers in Artificial Intelligence and Applications
Volume	325
ISSN (Print)	0922-6389
ISSN (Electronic)	1879-8314

Conference

Conference	24th European Conference on Artificial Intelligence, ECAI 2020, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020
Country/Territory	Spain
City	Santiago de Compostela, Online
Period	29/08/20 → 8/09/20

Funding

Acknowledgments. This project was partly funded by the NWO research programme 400.17.605 (VWData) and NWO VENI project 639.021.335.

Access to Document

10.3233/FAIA200168

https://ebooks.iospress.nl/volumearticle/54963

Persistent URL (handle)

Persistent link

Cite this

Joshi, U., Jacobs, C., & Urbani, J. (2020). Rewrite or not rewrite? ML-based algorithm selection for datalog query answering on knowledge graphs. In G. De Giacomo, A. Catala, B. Dilkina, M. Milano, S. Barro, A. Bugarin, & J. Lang (Eds.), ECAI 2020: 24th European Conference on Artificial Intelligence, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020 - Proceedings (pp. 792-799). (Frontiers in Artificial Intelligence and Applications; Vol. 325). IOS Press BV. https://doi.org/10.3233/FAIA200168

Joshi, Unmesh ; Jacobs, Ceriel ; Urbani, Jacopo. / Rewrite or not rewrite? ML-based algorithm selection for datalog query answering on knowledge graphs. ECAI 2020: 24th European Conference on Artificial Intelligence, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020 - Proceedings. editor / Giuseppe De Giacomo ; Alejandro Catala ; Bistra Dilkina ; Michela Milano ; Senen Barro ; Alberto Bugarin ; Jerome Lang. IOS Press BV, 2020. pp. 792-799 (Frontiers in Artificial Intelligence and Applications).

@inproceedings{ac22faa5fe66495e88c0a3dc2a66e047,

title = "Rewrite or not rewrite? ML-based algorithm selection for datalog query answering on knowledge graphs",

abstract = "Query-driven reasoning techniques with Datalog rules, like Magic Sets (MS), are ideal for implementing query answering on Knowledge Graphs (KGs). For some queries, executing a rewriting procedure like MS is the best choice, but for others a non-rewriting procedure like Query-subquery (QSQ) can be faster. Choosing beforehand which procedure should be used is not trivial and mistakes can be costly. To address this problem, we describe a first-of-its-kind method that builds a Machine Learning (ML) model to predict whether a query should be answered with MS or with QSQ. Experiments on several well-known KGs show that our method can return accurate predictions, and this leads to a significant reduction of the response time of query answering.",

author = "Unmesh Joshi and Ceriel Jacobs and Jacopo Urbani",

year = "2020",

doi = "10.3233/FAIA200168",

language = "English",

isbn = "9781643681009",

series = "Frontiers in Artificial Intelligence and Applications",

publisher = "IOS Press BV",

pages = "792--799",

editor = "\{De Giacomo\}, Giuseppe and Alejandro Catala and Bistra Dilkina and Michela Milano and Senen Barro and Alberto Bugarin and Jerome Lang",

booktitle = "ECAI 2020",

note = "24th European Conference on Artificial Intelligence, ECAI 2020, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020 ; Conference date: 29-08-2020 Through 08-09-2020",

}

Joshi, U, Jacobs, C & Urbani, J 2020, Rewrite or not rewrite? ML-based algorithm selection for datalog query answering on knowledge graphs. in G De Giacomo, A Catala, B Dilkina, M Milano, S Barro, A Bugarin & J Lang (eds), ECAI 2020: 24th European Conference on Artificial Intelligence, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020 - Proceedings. Frontiers in Artificial Intelligence and Applications, vol. 325, IOS Press BV, pp. 792-799, 24th European Conference on Artificial Intelligence, ECAI 2020, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020, Santiago de Compostela, Online, Spain, 29/08/20. https://doi.org/10.3233/FAIA200168

Rewrite or not rewrite? ML-based algorithm selection for datalog query answering on knowledge graphs. / Joshi, Unmesh; Jacobs, Ceriel; Urbani, Jacopo.
ECAI 2020: 24th European Conference on Artificial Intelligence, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020 - Proceedings. ed. / Giuseppe De Giacomo; Alejandro Catala; Bistra Dilkina; Michela Milano; Senen Barro; Alberto Bugarin; Jerome Lang. IOS Press BV, 2020. p. 792-799 (Frontiers in Artificial Intelligence and Applications; Vol. 325).

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Rewrite or not rewrite? ML-based algorithm selection for datalog query answering on knowledge graphs

AU - Joshi, Unmesh

AU - Jacobs, Ceriel

AU - Urbani, Jacopo

PY - 2020

Y1 - 2020

N2 - Query-driven reasoning techniques with Datalog rules, like Magic Sets (MS), are ideal for implementing query answering on Knowledge Graphs (KGs). For some queries, executing a rewriting procedure like MS is the best choice, but for others a non-rewriting procedure like Query-subquery (QSQ) can be faster. Choosing beforehand which procedure should be used is not trivial and mistakes can be costly. To address this problem, we describe a first-of-its-kind method that builds a Machine Learning (ML) model to predict whether a query should be answered with MS or with QSQ. Experiments on several well-known KGs show that our method can return accurate predictions, and this leads to a significant reduction of the response time of query answering.

AB - Query-driven reasoning techniques with Datalog rules, like Magic Sets (MS), are ideal for implementing query answering on Knowledge Graphs (KGs). For some queries, executing a rewriting procedure like MS is the best choice, but for others a non-rewriting procedure like Query-subquery (QSQ) can be faster. Choosing beforehand which procedure should be used is not trivial and mistakes can be costly. To address this problem, we describe a first-of-its-kind method that builds a Machine Learning (ML) model to predict whether a query should be answered with MS or with QSQ. Experiments on several well-known KGs show that our method can return accurate predictions, and this leads to a significant reduction of the response time of query answering.

UR - https://www.scopus.com/pages/publications/85091779502

UR - https://www.scopus.com/pages/publications/85091779502#tab=citedBy

U2 - 10.3233/FAIA200168

DO - 10.3233/FAIA200168

M3 - Conference contribution

AN - SCOPUS:85091779502

SN - 9781643681009

T3 - Frontiers in Artificial Intelligence and Applications

SP - 792

EP - 799

BT - ECAI 2020

A2 - De Giacomo, Giuseppe

A2 - Catala, Alejandro

A2 - Dilkina, Bistra

A2 - Milano, Michela

A2 - Barro, Senen

A2 - Bugarin, Alberto

A2 - Lang, Jerome

PB - IOS Press BV

T2 - 24th European Conference on Artificial Intelligence, ECAI 2020, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020

Y2 - 29 August 2020 through 8 September 2020

ER -

Joshi U, Jacobs C, Urbani J. Rewrite or not rewrite? ML-based algorithm selection for datalog query answering on knowledge graphs. In De Giacomo G, Catala A, Dilkina B, Milano M, Barro S, Bugarin A, Lang J, editors, ECAI 2020: 24th European Conference on Artificial Intelligence, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020 - Proceedings. IOS Press BV. 2020. p. 792-799. (Frontiers in Artificial Intelligence and Applications). Epub 2020 Aug 24. doi: 10.3233/FAIA200168

Rewrite or not rewrite? ML-based algorithm selection for datalog query answering on knowledge graphs

Abstract

Publication series

Conference

Funding

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this