An effective and efficient graph representation learning approach for big graphs

Simple item page
dc.contributor.authorSerra, Edoardo
dc.contributor.authorJoaristi, Mikel
dc.contributor.authorCuzzocrea, Alfredo
dc.contributor.authorSoufargi, Selim
dc.contributor.authorLeung, Carson
dc.date.accessioned2022-01-27T01:17:04Z
dc.date.available2022-01-27T01:17:04Z
dc.date.issued2021-09
dc.date.submitted2022-01-22T00:08:20Zen_US
dc.description.abstractIn the Big Data era, large graph datasets are becoming increasingly popular due to their capability to integrate and interconnect large sources of data in many fields, e.g., social media, biology, communication networks, etc. Graph representation learning is a flexible tool that automatically extracts features from a graph node. These features can be directly used for machine learning tasks. Graph representation learning approaches producing features preserving the structural information of the graphs are still an open problem, especially in the context of large-scale graphs. In this paper, we propose a new fast and scalable structural representation learning approach called SparseStruct. Our approach uses a sparse internal representation for each node, and we formally proved its ability to preserve structural information. Thanks to a light-weight algorithm where each iteration costs only linear time in the number of the edges, SparseStruct is able to easily process large graphs. In addition, it provides improvements in comparison with state of the art in terms of prediction and classification accuracy by also providing strong robustness to noise data.en_US
dc.description.sponsorshipNatural Sciences and Engineering Research Council of Canada (NSERC); University of Manitoba, Canadaen_US
dc.identifier.citationE. Serra, M. Joaristi, A. Cuzzocrea, S. Soufargi, C.K. Leung, An effective and efficient graph representation learning approach for big graphs.SEBD 2021: The 29th Italian Symposium on Advanced Database Systems, September 5-9, 2021, Pizzo Calabro (VV), Italy. http://ceur-ws.org/Vol-2994/paper13.pdfen_US
dc.identifier.issn1613-0073
dc.identifier.otherhttp://ceur-ws.org/Vol-2994/paper13.pdf
dc.identifier.urihttp://hdl.handle.net/1993/36219
dc.language.isoengen_US
dc.publisherCEUR Workshop Proceedingsen_US
dc.rightsopen accessen_US
dc.subjectgraph representation learningen_US
dc.subjectsparse representationen_US
dc.subjectlarge-scale graph structural representationen_US
dc.titleAn effective and efficient graph representation learning approach for big graphsen_US
dc.typeOtheren_US
local.author.affiliationFaculty of Scienceen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Serra_SEBD2021_SparseStruct.pdf
Size:
303.76 KB
Format:
Adobe Portable Document Format
Description:
Main article
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.24 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
University of Manitoba Scholarship
Faculty of Science Scholarly Works