Bottom-up Discovery of Context-aware Quality Constraints for Heterogeneous Knowledge Graphs

Wilcke, W.X.; Kleijn, Maurice de; Boer, Victor de; Scholten, H.J.; Harmelen, Frank van

doi:10.5220/0010113500750086

Cited by 2 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The knowledge graph created in this paper is based on the knowledge graph of the power industry based on multi-modal deep learning. The early knowledge graph is mainly developed from the graph database, while the current knowledge graph based on multi-modal deep learning mainly focuses on two modes: image and text [12][13] . Based on the existing research, the vision and other multimodal data in the knowledge graph based on deep multimodal learning have the functions of physical demonstration, disambiguation, and supplement of details, which can promote semantic understanding and have a positive impact on the construction and dissemination of knowledge.…”

Section: Research On Knowledge Graphmentioning

confidence: 99%

Construction of Multimodal Knowledge Graph for Power System

Feng,

Wang,

Peng

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

The professional vocabulary of the electric power industry is numerous, and the relationship is complex. How to mine valuable information from multi-source data of the power industry and describe the relationship between words is of great significance to assisting multi-business management of power systems. Aiming at the multimodal knowledge data of power systems, this paper uses the BiLSTM-CRF model and BiLSTM-Attention model to extract entity knowledge and relationship, respectively, and identifies image data through the CNN model. The experimental results show that the power industry knowledge graph based on multi-modal deep learning constructed in this paper can better realize the intelligent representation and management of many kinds of business in the power industry.

show abstract

Section: Research On Knowledge Graphmentioning

confidence: 99%

Construction of Multimodal Knowledge Graph for Power System

Feng,

Wang,

Peng

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

Discovering association rules from big graphs

Fan

Jin

et al. 2022

Proc. VLDB Endow.

View full text Add to dashboard Cite

This paper tackles two challenges to discovery of graph rules. Existing discovery methods often (a) return an excessive number of rules, and (b) do not scale with large graphs given the intractability of the discovery problem. We propose an application-driven strategy to cut back rules and data that are irrelevant to users' interests, by training a machine learning (ML) model to identify data pertaining to a given application. Moreover, we introduce a sampling method to reduce a big graph G to a set H of small sample graphs. Given expected support and recall bounds, the method is able to deduce samples in H and mine rules from H to satisfy the bounds in the entire G . As proof of concept, we develop an algorithm to discover Graph Association Rules (GARs), which are a combination of graph patterns and attribute dependencies, and may embed ML classifiers as predicates. We show that the algorithm is parallelly scalable, i.e. , it guarantees to reduce runtime when more machines are used. We experimentally verify that the method is able to discover rules with recall above 91% when using sample ratio 10%, with speedup of 61 times.

show abstract

Bottom-up Discovery of Context-aware Quality Constraints for Heterogeneous Knowledge Graphs

Cited by 2 publications

References 19 publications

Construction of Multimodal Knowledge Graph for Power System

Construction of Multimodal Knowledge Graph for Power System

Discovering association rules from big graphs

Contact Info

Product

Resources

About