Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning

TL;DR

This paper introduces MINERVA, a reinforcement learning method that navigates knowledge graphs to answer queries with known relations and one entity, achieving state-of-the-art results in link prediction tasks.

Contribution

The paper presents a novel neural reinforcement learning algorithm for reasoning over knowledge bases, effectively handling the challenging task of question answering with incomplete paths.

Findings

MINERVA outperforms previous models on multiple datasets

Reinforcement learning effectively guides path navigation in large knowledge graphs

The approach significantly improves link prediction accuracy

Abstract

Knowledge bases (KB), both automatically and manually constructed, are often incomplete --- many valid facts can be inferred from the KB by synthesizing existing information. A popular approach to KB completion is to infer new relations by combinatory reasoning over the information found along other paths connecting a pair of entities. Given the enormous size of KBs and the exponential number of paths, previous path-based models have considered only the problem of predicting a missing relation given two entities or evaluating the truth of a proposed triple. Additionally, these methods have traditionally used random paths between fixed entity pairs or more recently learned to pick paths between them. We propose a new algorithm MINERVA, which addresses the much more difficult and practical task of answering questions where the relation is known, but only one entity. Since random walks are impractical in a setting with combinatorially many destinations from a start node, we present a neural reinforcement learning approach which learns how to navigate the graph conditioned on the input query to find predictive paths. Empirically, this approach obtains state-of-the-art results on several datasets, significantly outperforming prior methods.