DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning

TL;DR

DeepPath introduces a reinforcement learning framework that enables reasoning over large knowledge graphs by learning multi-hop relational paths, improving accuracy, diversity, and efficiency over previous methods.

Contribution

The paper presents a novel reinforcement learning approach using continuous states and a reward function for reasoning in knowledge graphs, outperforming prior algorithms.

Findings

Outperforms path-ranking algorithms on Freebase

Achieves better results than knowledge graph embedding methods

Enhances reasoning efficiency and diversity

Abstract

We study the problem of learning to reason in large scale knowledge graphs (KGs). More specifically, we describe a novel reinforcement learning framework for learning multi-hop relational paths: we use a policy-based agent with continuous states based on knowledge graph embeddings, which reasons in a KG vector space by sampling the most promising relation to extend its path. In contrast to prior work, our approach includes a reward function that takes the accuracy, diversity, and efficiency into consideration. Experimentally, we show that our proposed method outperforms a path-ranking based algorithm and knowledge graph embedding methods on Freebase and Never-Ending Language Learning datasets.