File(s) under permanent embargo
Topological graph representation learning on property graph
conference contribution
posted on 2020-01-01, 00:00 authored by Y Zhang, D Gao, A K Cherukuri, L Wang, S Pan, Shu LiProperty graph representation learning is using the property features from the graph to build the embeddings over the nodes and edges. There are many graph application tasks are using the property graph representation learning as part of the process. However, existing methods on Property graph representation learning ignore either the property features or the global topological structure information. We propose the TPGL, which utilizes the topological data analysis with a bias property graph representation learning strategy. The topological data analysis could augment the global topological information to the embedding and significantly improve the embedding performance on node classification experiments. Moreover, the designed bias strategy aggregated the property features into node embedding by using GNN. Particularly, the proposed TPGL outperformed the start of the art methods including PGE in node classification tasks on public datasets.
History
Event
KSEM Knowledge Science, Engineering and Management. International Conference (13th : 2020 : Hangzhou, China)Volume
12274 LNAISeries
Lecture Notes in Artificial Intelligence (LNAI)Pagination
53 - 64Publisher
Springer ChamLocation
Hangzhou, ChinaPlace of publication
Cham, SwitzerlandPublisher DOI
Start date
2020-08-28End date
2020-08-30ISSN
0302-9743eISSN
1611-3349ISBN-13
9783030551292Language
engPublication classification
E1 Full written paper - refereedCopyright notice
2020, Springer Nature Switzerland AGEditor/Contributor(s)
Gang Li, Heng Shen, Ye Yuan, Xiaoyang Wang, Huawen Liu, Xiang ZhaoTitle of proceedings
KSEM 2020 : Proceedings of Part 1 of the 13th International Conference on Knowledge Science, Enginerring and ManagementUsage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC