File(s) under permanent embargo
PDKE: an efficient distributed embedding framework for large knowledge graphs
conference contribution
posted on 2020-09-01, 00:00 authored by S Dong, X Wang, L Chai, Jianxin LiJianxin Li, Y YangKnowledge Representation Learning (KRL) methods produce unsupervised node features from knowledge graphs that can be used for a variety of machine learning tasks. However, two main issues in KRL embedding techniques have not been addressed yet. One is that real-world knowledge graphs contain millions of nodes and billions of edges, which exceeds the capability of existing KRL embedding systems; the other issue is the lack of a unified framework to integrate the current KRL models to facilitate the realization of embeddings for various applications. To address the issues, we propose PDKE, which is a distributed KRL training framework that can incorporate different translation-based KRL models using a unified algorithm template. In PDKE, a set of functions is implemented by various knowledge embedding models to form a unified algorithm template for distributed KRL. PDKE implements training arbitrarily large embeddings in a distributed environment. The effeciency and scalability of our framework have been verified by extensive experiments on both synthetic and real-world knowledge graphs, which shows that our approach outperforms the existing ones by a large margin.
History
Event
DASFAA Database Systems for Advanced Applications. International Conference (25th : 2020 : Jeju, South Korea)Volume
LNCS Vol 12113Series
Lecture Notes in Computer SciencePagination
588 - 603Publisher
SpringerLocation
Jeju, South KoreaPlace of publication
Cham, SwitzerlandPublisher DOI
Start date
2020-09-24End date
2020-09-27ISSN
0302-9743eISSN
1611-3349ISBN-13
9783030594152Language
engPublication classification
E1 Full written paper - refereedCopyright notice
2020, Springer Nature SwitzerlandEditor/Contributor(s)
Yunmook Nah, Bin Cui, Sang-Won Lee, Jeffrey Yu, Yang-Sae Moon, Steven WhangTitle of proceedings
DASFAA 2020 : Proceedings of the 25th International Conference on Database Systems for Advanced ApplicationsUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC