论文推荐|知识图推理的强化学习方法（EMNLP’17）

论文题目

DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning

作者：

Wenhan Xiong ；

Thien Hoang ；

William Yang Wang；

推荐理由：

这篇文章首次将强化学习的思想引入到知识图谱的推理过程中，企图找到多跳（h，r，？）问题推理的最佳路径。文章首先将所有的节点进行embedding，然后训练一个简单的policy network，输入（当前节点的embedding，到目标节点的embedding之间的差），输出所有要采取的relation的分布（即policy）。

训练方法比较粗糙，使用基本的policy gradient，每次的路径找到目标给一个奖励，找不到-1。但是可以给基于认知的推理很多启发。

摘要：

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 ef- ficiency 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.1

学术头条已建立微信交流群，想进群的同学请加学术君微信：AMiner308，记得备注：名字+单位/学校噢！