Equivariant Contrastive Learning for Sequential Recommendation

Contrastive learning (CL) benefits the training of sequential recommendation models with informative self-supervision signals. Existing solutions apply general sequential data augmentation strategies to generate positive pairs and encourage their representations to be invariant. However, due to the...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-03
Hauptverfasser:	Zhou, Peilin, Gao, Jingqi, Xie, Yueqi, Ye, Qichen, Hua, Yining, Kim, Jae Boum, Wang, Shoujin, Kim, Sunghun
Format:	Artikel
Sprache:	eng
Schlagworte:	Coders Data augmentation Invariants Learning Representations Source code Substitutes User behavior
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!