DAGE: DAG query answering via relational combinator with logical constraints
DAGE: DAG query answering via relational combinator with logical constraints
Predicting answers to queries over knowledge graphs is called a complex reasoning task because answering a query requires subdividing it into subqueries. Existing query embedding methods use this decomposition to compute the embedding of a query as the combination of the embedding of the subqueries. This requirement limits the answerable queries to queries having a single free variable and being decomposable, which are called tree-form queries and correspond to the SROI- description logic. In this paper, we define a more general set of queries, called DAG queries and formulated in the ALCOIR description logic, propose a query embedding method for them, called DAGE, and a new benchmark to evaluate query embeddings on them. Given the computational graph of a DAG query, DAGE combines the possibly multiple paths between two nodes into a single path with a trainable operator that represents the intersection of relations and learns DAG-DL concepts from tautologies. We implement DAGE on top of existing query embedding methods, and we empirically measure the improvement of our method over the results of vanilla methods evaluated in tree-form queries that approximate the DAG queries of our proposed benchmark.
Complex Query Answering, Description Logic, Knowledge Graph
2514-2529
Association for Computing Machinery
He, Yunjie
e92ec3e3-2008-464b-9e37-694ad05264aa
Xiong, Bo
d8c3ce0a-07ac-43f8-bd67-f230c6cbc1ec
Hernandez, Daniel
39723173-ccff-4015-b506-cec5aec76936
Zhu, Yuqicheng
e2164ad8-3ba3-4dd5-9a6f-81f253f938c6
Kharlamov, Evgenyi
5a522384-6a70-4f2c-ab5a-6b95c1944b32
Staab, Steffen
bf48d51b-bd11-4d58-8e1c-4e6e03b30c49
22 April 2025
He, Yunjie
e92ec3e3-2008-464b-9e37-694ad05264aa
Xiong, Bo
d8c3ce0a-07ac-43f8-bd67-f230c6cbc1ec
Hernandez, Daniel
39723173-ccff-4015-b506-cec5aec76936
Zhu, Yuqicheng
e2164ad8-3ba3-4dd5-9a6f-81f253f938c6
Kharlamov, Evgenyi
5a522384-6a70-4f2c-ab5a-6b95c1944b32
Staab, Steffen
bf48d51b-bd11-4d58-8e1c-4e6e03b30c49
He, Yunjie, Xiong, Bo, Hernandez, Daniel, Zhu, Yuqicheng, Kharlamov, Evgenyi and Staab, Steffen
(2025)
DAGE: DAG query answering via relational combinator with logical constraints.
In WWW '25: Proceedings of the ACM on Web Conference 2025.
Association for Computing Machinery.
.
(doi:10.1145/3696410.3714677).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Predicting answers to queries over knowledge graphs is called a complex reasoning task because answering a query requires subdividing it into subqueries. Existing query embedding methods use this decomposition to compute the embedding of a query as the combination of the embedding of the subqueries. This requirement limits the answerable queries to queries having a single free variable and being decomposable, which are called tree-form queries and correspond to the SROI- description logic. In this paper, we define a more general set of queries, called DAG queries and formulated in the ALCOIR description logic, propose a query embedding method for them, called DAGE, and a new benchmark to evaluate query embeddings on them. Given the computational graph of a DAG query, DAGE combines the possibly multiple paths between two nodes into a single path with a trainable operator that represents the intersection of relations and learns DAG-DL concepts from tautologies. We implement DAGE on top of existing query embedding methods, and we empirically measure the improvement of our method over the results of vanilla methods evaluated in tree-form queries that approximate the DAG queries of our proposed benchmark.
Text
3696410.3714677
- Version of Record
More information
Published date: 22 April 2025
Venue - Dates:
The Web Conference: WWW, , Sydney, Australia, 2025-04-28 - 2025-05-02
Keywords:
Complex Query Answering, Description Logic, Knowledge Graph
Identifiers
Local EPrints ID: 502878
URI: http://eprints.soton.ac.uk/id/eprint/502878
PURE UUID: 9ae2b4e0-1ebc-42cd-9ac7-e582df4ecebe
Catalogue record
Date deposited: 10 Jul 2025 17:21
Last modified: 11 Sep 2025 02:45
Export record
Altmetrics
Contributors
Author:
Yunjie He
Author:
Bo Xiong
Author:
Daniel Hernandez
Author:
Yuqicheng Zhu
Author:
Evgenyi Kharlamov
Author:
Steffen Staab
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics