DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
DeepPath: метод обучения с подкреплением для логического вывода в графах знаний
2017-01-01
SCID: 54.1/9kcmjn3n
Discuss with AI
Freebaseknowledge graph embeddingsknowledge graph reasoningmulti-hop relational pathsreinforcement learning
Figures from the paper
Abstract (AI)
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.1
Key Findings
1
A policy-based agent uses continuous states derived from knowledge graph embeddings to sample promising relations while extending reasoning paths.
2
DeepPath introduces a reinforcement learning framework for learning multi-hop relational paths in large-scale knowledge graphs.
3
Experiments on Freebase and Never-Ending Language Learning datasets show DeepPath outperforming a path-ranking algorithm and knowledge graph embedding methods.
4
The reward function jointly accounts for path accuracy, diversity, and efficiency, unlike prior approaches focused primarily on accuracy.
Research Object
multi-hop relational paths in large-scale knowledge graphs
Research Subject
learning to reason over these paths, with accuracy, diversity, and efficiency of path selection as the focal aspects
Publication Details
Publication Date
2017-01-01
Journal
Publisher
ISSN
Cited by
859
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai7
ImageNet classification with deep convolutional neural networks2017
Adam: A Method for Stochastic Optimization2014
Convolutional Neural Networks for Sentence Classification2014
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups2012
Knowledge Graph Embedding by Translating on Hyperplanes2014
Learning Entity and Relation Embeddings for Knowledge Graph Completion2015
Knowledge Graph Embedding via Dynamic Mapping Matrix2015
Cited by7
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications2021
A Metaverse: Taxonomy, Components, Applications, and Open Challenges2022
Deep Learning on Graphs: A Survey2020
Knowledge Graphs: Opportunities and Challenges2023
Knowledge graph and knowledge reasoning: A systematic review2022
AgentAI: A comprehensive survey on autonomous agents in distributed AI for industry 4.02025
Research hypothesis generation over scientific knowledge graphs2025