Show simple item record

dc.contributor.authorYu, Junliang
dc.contributor.authorYin, Hongzhi
dc.contributor.authorGao, Min
dc.contributor.authorXia, Xin
dc.contributor.authorZhang, Xiangliang
dc.contributor.authorNguyen, Quoc Viet Hung
dc.date.accessioned2021-09-13T00:17:17Z
dc.date.available2021-09-13T00:17:17Z
dc.date.issued2021
dc.identifier.isbn978-1-4503-8332-5
dc.identifier.doi10.1145/3447548.3467340
dc.identifier.urihttp://hdl.handle.net/10072/407872
dc.description.abstractSelf-supervised learning (SSL), which can automatically generate ground-truth samples from raw data, holds vast potential to improve recommender systems. Most existing SSL-based methods perturb the raw data graph with uniform node/edge dropout to generate new data views and then conduct the self-discrimination based contrastive learning over different views to learn generalizable representations. Under this scheme, only a bijective mapping is built between nodes in two different views, which means that the self-supervision signals from other nodes are being neglected. Due to the widely observed homophily in recommender systems, we argue that the supervisory signals from other nodes are also highly likely to benefit the representation learning for recommendation. To capture these signals, a general socially-aware SSL framework that integrates tri-training is proposed in this paper. Technically, our framework first augments the user data views with the user social information. And then under the regime of tri-training for multi-view encoding, the framework builds three graph encoders (one for recommendation) upon the augmented views and iteratively improves each encoder with self-supervision signals from other users, generated by the other two encoders. Since the tri-training operates on the augmented views of the same data sources for self-supervision signals, we name it self-supervised tri-training. Extensive experiments on multiple real-world datasets consistently validate the effectiveness of the self-supervised tri-training framework for improving recommendation. The code is released at https://github.com/Coder-Yu/QRec.
dc.description.peerreviewedYes
dc.publisherACM
dc.relation.ispartofconferencenameThe 27th ACM SIGKDD Conference On Knowledge Discovery and Data Mining (KDD'21)
dc.relation.ispartofconferencetitleKDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining
dc.relation.ispartofdatefrom2021-08-14
dc.relation.ispartofdateto2021-08-18
dc.relation.ispartoflocationSingapore
dc.subject.fieldofresearchInformation systems
dc.subject.fieldofresearchcode4609
dc.titleSocially-Aware Self-Supervised Tri-Training for Recommendation
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationYu, J; Yin, H; Gao, M; Xia, X; Zhang, X; Nguyen, QVH, Socially-Aware Self-Supervised Tri-Training for Recommendation, KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021
dc.date.updated2021-09-13T00:12:18Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© ACM, 2021. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, ISBN: 978-1-4503-8332-5, https://doi.org/10.1145/3447548.3467340
gro.hasfulltextFull Text
gro.griffith.authorNguyen, Henry


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record