One Model, Any Conjunctive Query: Graph Neural Networks for Answering Queries over Incomplete Knowledge Graphs

TL;DR

This paper introduces AnyCQ, a graph neural network model that answers conjunctive queries over incomplete knowledge graphs, generalizing from small training instances to large, complex queries and transferring across different graphs.

Contribution

The paper presents a novel GNN-based framework, AnyCQ, capable of answering conjunctive queries on any knowledge graph, including large and unseen ones, using reinforcement learning training.

Findings

AnyCQ generalizes to large, complex queries.

It outperforms existing methods on new benchmarks.

It effectively transfers to new knowledge graphs with link prediction.

Abstract

Motivated by the incompleteness of modern knowledge graphs, a new setup for query answering has emerged, where the goal is to predict answers that do not necessarily appear in the knowledge graph, but are present in its completion. In this paper, we formally introduce and study two query answering problems, namely, query answer classification and query answer retrieval. To solve these problems, we propose AnyCQ, a model that can classify answers to any conjunctive query on any knowledge graph. At the core of our framework lies a graph neural network trained using a reinforcement learning objective to answer Boolean queries. Trained only on simple, small instances, AnyCQ generalizes to large queries of arbitrary structure, reliably classifying and retrieving answers to queries that existing approaches fail to handle. This is empirically validated through our newly proposed, challenging benchmarks. Finally, we empirically show that AnyCQ can effectively transfer to completely novel knowledge graphs when equipped with an appropriate link prediction model, highlighting its potential for querying incomplete data.