Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization

TL;DR

This paper introduces QTO, a novel method for answering complex logical queries on knowledge graphs by efficiently finding the exact optimal solution through query computation tree optimization, outperforming previous methods.

Contribution

QTO leverages query computation tree optimization to efficiently compute exact solutions, significantly improving accuracy and interpretability in complex knowledge graph query answering.

Findings

QTO achieves state-of-the-art performance, outperforming previous methods by 22%.

QTO can interpret intermediate solutions with over 90% accuracy.

Experiments on 3 datasets validate the effectiveness of QTO.

Abstract

Answering complex logical queries on incomplete knowledge graphs is a challenging task, and has been widely studied. Embedding-based methods require training on complex queries, and cannot generalize well to out-of-distribution query structures. Recent work frames this task as an end-to-end optimization problem, and it only requires a pretrained link predictor. However, due to the exponentially large combinatorial search space, the optimal solution can only be approximated, limiting the final accuracy. In this work, we propose QTO (Query Computation Tree Optimization) that can efficiently find the exact optimal solution. QTO finds the optimal solution by a forward-backward propagation on the tree-like computation graph, i.e., query computation tree. In particular, QTO utilizes the independence encoded in the query computation tree to reduce the search space, where only local computations are involved during the optimization procedure. Experiments on 3 datasets show that QTO obtains state-of-the-art performance on complex query answering, outperforming previous best results by an average of 22%. Moreover, QTO can interpret the intermediate solutions for each of the one-hop atoms in the query with over 90% accuracy. The code of our paper is at https://github.com/bys0318/QTO.