000 03676naa a22005657i 4500
001 UMUN-OA-20261005-CYB-025
003 local
005 20261005174815.0
006 m o d
007 cr||||||||||||
008 261005s2022 xx o u000 0 eng d
024 7 _a10.1038/s41467-022-30714-9
_2doi
035 _a(local)OpenAlex:W4281686206
040 _alocal
_beng
_clocal
041 0 _aeng
100 0 _aChuhan Wu
_eauthor.
245 1 2 _aA federated graph neural network framework for privacy-preserving personalization /
_cChuhan Wu; Fangzhao Wu; Lingjuan Lyu [and others].
264 1 _a[Place of publication not identified] :
_bNature Portfolio,
_c2022.
300 _a1 online resource (1 article).
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
500 _aPublication type: Journal article.
500 _aLinked open-access copy: published version.
506 0 _aOpen access; no subscription required for the linked open-access version.
_fUnrestricted online access
_2star
520 3 _aGraph neural network (GNN) is effective in modeling high-order interactions and has been widely used in various personalized applications such as recommendation. However, mainstream personalization methods rely on centralized GNN learning on global graphs, which have considerable privacy risks due to the privacy-sensitive nature of user data. Here, we present a federated GNN framework named FedPerGNN for both effective and privacy-preserving personalization. Through a privacy-preserving model update method, we can collaboratively train GNN models based on decentralized graphs inferred from local data. To further exploit graph information beyond local interactions, we introduce a privacy-preserving graph expansion protocol to incorporate high-order information under privacy protection. Experimental results on six datasets for personalization in different scenarios show that FedPerGNN achieves 4.0% ~ 9.6% lower errors than the state-of-the-art federated personalization methods under good privacy protection. FedPerGNN provides a promising direction to mining decentralized graph data in a privacy-preserving manner for responsible and intelligent personalization.
540 _aCreative Commons Attribution (licence family recorded by the source; version not supplied in metadata).
_uhttps://openalex.org/W4281686206
546 _aIn English.
588 0 _aDescription generated from OpenAlex bibliographic metadata retrieved on 5 October 2026; full text linked from the source.
590 _aCourse allocation: B. Sc. Cyber Security.
650 4 _afederated learning
650 4 _agraph neural networks
650 4 _aprivacy-preserving personalization
650 4 _arecommender systems
650 4 _agraph expansion
650 4 _ahigher-order interactions
653 _aB. Sc. Cyber Security
653 _aUMUN open access collection
653 _aprivacy preserving
655 4 _aJournal articles.
700 0 _aFangzhao Wu
_eauthor.
700 0 _aLingjuan Lyu
_eauthor.
700 0 _aTao Qi
_eauthor.
700 0 _aYongfeng Huang
_eauthor.
700 0 _aXing Xie
_eauthor.
773 0 _tNature Communications
_gVol. 13, no. 1, (2022), pages/article 3091
_x2041-1723
856 4 0 _uhttps://www.nature.com/articles/s41467-022-30714-9.pdf
_yRead open-access publication
_zOpen access. Access and licence reported by the source; this host could not be independently checked by automation.
_70
884 _aCourse selection and automated MARC21 enrichment from OpenAlex metadata.
_g20261005
_khttps://openalex.org/W4281686206
_qlocal
942 _n0
999 _c452
_d452