ADRL: An attention-based deep reinforcement learning framework for knowledge graph reasoning

Wang, Qi; Hao, Yongsheng; Cao, Jie

doi:10.1016/j.knosys.2020.105910

Cited by 39 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most related tasks to rule mining is KG reasoning [4,36,37]. Those applications utilize RL to solve the optimization problems such as finding an optimal path in the KG.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Rule Mining over Knowledge Graphs via Reinforcement Learning

Chen,

Jiang,

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

Knowledge graphs (KGs) are an important source repository for a wide range of applications and rule mining from KGs recently attracts wide research interest in the KG-related research community. Many solutions have been proposed for the rule mining from large-scale KGs, which however are limited in the inefficiency of rule generation and ineffectiveness of rule evaluation. To solve these problems, in this paper we propose a generation-then-evaluation rule mining approach guided by reinforcement learning. Specifically, a two-phased framework is designed.The first phase aims to train a reinforcement learning agent for rule generation from KGs, and the second is to utilize the value function of the agent to guide the step-by-step rule generation. We conduct extensive experiments on several datasets and the results prove that our rule mining solution achieves state-ofthe-art performance in terms of efficiency and effectiveness.

show abstract

“…The most related tasks to rule mining is KG reasoning [4,36,37]. Those applications utilize RL to solve the optimization problems such as finding an optimal path in the KG.…”

Section: Related Workmentioning

confidence: 99%

“…Knowledge graphs (KGs) such as FreeBase [1], DBpedia [2], and Wikidata [3] draw much attention due to their wide range of applications including reasoning [4] and recommendation [5], etc. The usefulness of KGs lies in their large-scale high-quality well-structured facts which are usually extracted from text corpora.…”

Section: Introductionmentioning

confidence: 99%

Rule Mining over Knowledge Graphs via Reinforcement Learning

Chen,

Jiang,

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The output is then the weighted sum of the values, where the weights are provided by the attention vector. This mechanism has been widely used in Deep RL ( Bramlage and Cortese, 2021 , Iqbal and Sha, 2019 , Manchin et al, 2019 , Mott et al, 2019 , Parisotto et al, 2020 , Shen et al, 2019 , Wang et al, 2020 , Zambaldi et al, 2018 ) and has been involved in achieving start-of-the-art results ( Vinyals et al, 2019 ).…”

Section: Related Workmentioning

confidence: 99%

Selective particle attention: Rapidly and flexibly selecting features for deep reinforcement learning

Blakeman

Mareschal

2022

Neural Networks

View full text Add to dashboard Cite

“…Less thought has been given to examining the hierarchical construction for KG reasoning, which exhibits performance improvement for modeling multiple semantics. Wan et al [173] introduce a framework called HRL (hierarchical reinforcement learning) that functions by augmenting the whole action into sub-actions. The component is carried out by a progression of the high to low-level policy.…”

Section: Reinforcement Learning For Knowledge Graph Completionmentioning

confidence: 99%

A Birds Eye View on Knowledge Graph Embeddings, Software Libraries, Applications and Challenges

Garg¹,

Roy²

2022

Preprint

View full text Add to dashboard Cite

In recent years, Knowledge Graph (KG) development has attracted significant researches considering the applications in web search, relation prediction, natural language processing, information retrieval, question answering to name a few. However, often KGs are incomplete due to which Knowledge Graph Completion (KGC) has emerged as a sub-domain of research to automatically track down the missing connections in a KG. Numerous strategies have been suggested to work out the KGC dependent on different representation procedures intended to embed triples into a low-dimensional vector space. Given the difficulties related to KGC, researchers around the world are attempting to comprehend the attributes of the problem statement. This study intends to provide an overview of knowledge bases combined with different challenges and their impacts. We discuss existing KGC approaches, including the state-of-the-art Knowledge Graph Embeddings (KGE), not only on static graphs but also for the latest trends such as multimodal, temporal, and uncertain knowledge graphs. In addition, reinforcement learning techniques are reviewed to model complex queries as a link prediction problem. Subsequently, we explored popular software packages for model training and examine open research challenges that can guide future research.

show abstract

ADRL: An attention-based deep reinforcement learning framework for knowledge graph reasoning

Cited by 39 publications

References 17 publications

Rule Mining over Knowledge Graphs via Reinforcement Learning

Rule Mining over Knowledge Graphs via Reinforcement Learning

Selective particle attention: Rapidly and flexibly selecting features for deep reinforcement learning

A Birds Eye View on Knowledge Graph Embeddings, Software Libraries, Applications and Challenges

Contact Info

Product

Resources

About