DAGE: DAG Query Answering via Relational Combinator with Logical Constraints

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Yunjie, Xiong, Bo, Hernández, Daniel, Zhu, Yuqicheng, Kharlamov, Evgeny, Staab, Steffen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929730962325504
author He, Yunjie
Xiong, Bo
Hernández, Daniel
Zhu, Yuqicheng
Kharlamov, Evgeny
Staab, Steffen
author_facet He, Yunjie
Xiong, Bo
Hernández, Daniel
Zhu, Yuqicheng
Kharlamov, Evgeny
Staab, Steffen
contents 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 $\mathcal{SROI}^-$ description logic. In this paper, we define a more general set of queries, called DAG queries and formulated in the $\mathcal{ALCOIR}$ 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 from tautologies. We show that it is possible to 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22105
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DAGE: DAG Query Answering via Relational Combinator with Logical Constraints
He, Yunjie
Xiong, Bo
Hernández, Daniel
Zhu, Yuqicheng
Kharlamov, Evgeny
Staab, Steffen
Databases
Artificial Intelligence
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 $\mathcal{SROI}^-$ description logic. In this paper, we define a more general set of queries, called DAG queries and formulated in the $\mathcal{ALCOIR}$ 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 from tautologies. We show that it is possible to 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.
title DAGE: DAG Query Answering via Relational Combinator with Logical Constraints
topic Databases
Artificial Intelligence
url https://arxiv.org/abs/2410.22105