DAGE: DAG Query Answering via Relational Combinator with Logical Constraints

TL;DR

This paper introduces DAGE, a novel method for answering complex DAG queries over knowledge graphs, extending beyond tree-form queries, with a new benchmark demonstrating improved performance over existing methods.

Contribution

The paper proposes DAGE, a new query embedding approach for DAG queries in the $ ext{ALCOIR}$ logic, and introduces a benchmark to evaluate its effectiveness.

Findings

DAGE effectively combines multiple paths into a single path using trainable operators.

DAGE can be implemented on top of existing query embedding methods.

Empirical results show DAGE outperforms vanilla methods on DAG queries.

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 $\mathcal{SROI}^-$ 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.