DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
复制标题
DOI：
10.18653/v1/d17-1060
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
Wenhan Xiong;Thi-Lan-Giao Hoang;William Yang Wang
中科院分区：
文献类型：
--
作者：
Wenhan Xiong;Thi-Lan-Giao Hoang;William Yang Wang
我们研究大规模知识图（KG）中学习推理的问题。更具体地说，我们描述了一种用于学习多跳关系路径的新型强化学习框架：我们使用基于知识图嵌入的具有连续状态的基于策略的代理，它通过采样最有希望的关系来扩展其路径，从而在 KG 向量空间中进行推理。与之前的工作相比，我们的方法包括考虑准确性、多样性和效率的奖励函数。实验表明，我们提出的方法在 Freebase 和 Never-Ending Language Learning 数据集上优于基于路径排名的算法和知识图嵌入方法。
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.