SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning

TL;DR

This paper introduces SQALER, a scalable method for question answering over knowledge graphs that separates multi-hop and logical reasoning, enabling efficient and effective reasoning on large graphs.

Contribution

It proposes a novel approach to decouple multi-hop and logical reasoning, scaling linearly with relation types and improving performance and scalability in knowledge graph question answering.

Findings

Achieves state-of-the-art on WebQuestionsSP

Solves the multi-hop MetaQA dataset effectively

Orders of magnitude more scalable than existing methods

Abstract

State-of-the-art approaches to reasoning and question answering over knowledge graphs (KGs) usually scale with the number of edges and can only be applied effectively on small instance-dependent subgraphs. In this paper, we address this issue by showing that multi-hop and more complex logical reasoning can be accomplished separately without losing expressive power. Motivated by this insight, we propose an approach to multi-hop reasoning that scales linearly with the number of relation types in the graph, which is usually significantly smaller than the number of edges or nodes. This produces a set of candidate solutions that can be provably refined to recover the solution to the original problem. Our experiments on knowledge-based question answering show that our approach solves the multi-hop MetaQA dataset, achieves a new state-of-the-art on the more challenging WebQuestionsSP, is orders of magnitude more scalable than competitive approaches, and can achieve compositional generalization out of the training distribution.