DeepAI AI Chat
Log In Sign Up

DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning

by   Wenhan Xiong, et al.
The Regents of the University of California

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.


page 1

page 2

page 3

page 4


Learning to Walk with Dual Agents for Knowledge Graph Reasoning

Graph walking based on reinforcement learning (RL) has shown great succe...

Reinforcement Knowledge Graph Reasoning for Explainable Recommendation

Recent advances in personalized recommendation have sparked great intere...

Multi-Hop Knowledge Graph Reasoning with Reward Shaping

Multi-hop reasoning is an effective approach for query answering (QA) ov...

Reinforced Anytime Bottom Up Rule Learning for Knowledge Graph Completion

Most of todays work on knowledge graph completion is concerned with sub-...

Inducing Interpretability in Knowledge Graph Embeddings

We study the problem of inducing interpretability in KG embeddings. Spec...

Efficient Knowledge Graph Accuracy Evaluation

Estimation of the accuracy of a large-scale knowledge graph (KG) often r...