VTechWorks staff will be away for the winter holidays starting Tuesday, December 24, 2024, through Wednesday, January 1, 2025, and will not be replying to requests during this time. Thank you for your patience, and happy holidays!
 

Augmenting Knowledge Transfer across Graphs

Simple item page
dc.contributor.authorMao, Yuzhenen
dc.contributor.authorSun, Jianhuien
dc.contributor.authorZhou, Daweien
dc.date.accessioned2023-03-01T13:45:29Zen
dc.date.available2023-03-01T13:45:29Zen
dc.date.issued2022-11en
dc.date.updated2023-03-01T04:15:53Zen
dc.description.abstractGiven a resource-rich source graph and a resource-scarce target graph, how can we effectively transfer knowledge across graphs and ensure a good generalization performance? In many high-impact domains (e.g., brain networks and molecular graphs), collecting and annotating data is prohibitively expensive and time-consuming, which makes domain adaptation an attractive option to alleviate the label scarcity issue. In light of this, the state-of-the-art methods focus on deriving domain-invariant graph representation that minimizes the domain discrepancy. However, it has recently been shown that a small domain discrepancy loss may not always guarantee a good generalization performance, especially in the presence of disparate graph structures and label distribution shifts. In this paper, we present TRANSNET, a generic learning framework for augmenting knowledge transfer across graphs. In particular, we introduce a novel notion named trinity signal that can naturally formulate various graph signals at different granularity (e.g., node attributes, edges, and subgraphs). With that, we further propose a domain unification module together with a trinity-signal mixup scheme to jointly minimize the domain discrepancy and augment the knowledge transfer across graphs. Finally, comprehensive empirical results show that TRANSNET outperforms all existing approaches on seven benchmark datasets by a significant margin.en
dc.description.versionAccepted versionen
dc.format.extentPages 1101-1106en
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.1109/ICDM54844.2022.00138en
dc.identifier.isbn9781665450997en
dc.identifier.issn1550-4786en
dc.identifier.urihttp://hdl.handle.net/10919/114014en
dc.identifier.volume2022-Novemberen
dc.language.isoenen
dc.publisherIEEEen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.titleAugmenting Knowledge Transfer across Graphsen
dc.title.serialProceedings - IEEE International Conference on Data Mining, ICDMen
dc.typeConference proceedingen
dc.type.dcmitypeTexten
dc.type.otherConference Proceedingen
pubs.finish-date2022-12-01en
pubs.organisational-group/Virginia Techen
pubs.organisational-group/Virginia Tech/Engineeringen
pubs.organisational-group/Virginia Tech/Engineering/Computer Scienceen
pubs.organisational-group/Virginia Tech/All T&R Facultyen
pubs.organisational-group/Virginia Tech/Engineering/COE T&R Facultyen
pubs.start-date2022-11-28en

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2212.04725.pdf
Size:
503.82 KB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download

Collections

All Faculty Deposits
Scholarly Works, Computer Science