WebMar 2, 2024 · Recently, contrastive self-supervised learning has become successful in recommendation. In light of this, we propose a Heterogeneous Graph Contrastive … WebJul 23, 2024 · Graph Convolution Network (GCN) has been applied in recommendation with various architectures for its representation learning capability in graph-structured …
Data Intelligence Lab@HKU - Google Sites
WebMay 1, 2024 · As self-supervised learning (SSL) has proven to be effective in the field of recommender systems [1,23,29,32], researchers have sought to leverage this paradigm … WebContrastive Learning for Cold-Start Recommendation. In Proceedings of MM. Ga Wu, Maksims Volkovs, Chee Loong Soon, Scott Sanner, and Himanshu Rai. 2024. Noise … brave bear directed drawing
Self-guided Contrastive Learning for Sequential Recommendation
WebI am an Assistant Professor at the Department of Computer Science in the University of Hong Kong (HKU). I am the director of Data Intelligence Lab@HKU, with the focus on developing novel machine learning frameworks to tackle various challenges in Data Mining, Information Retrieval, Spatial-Temporal Data Analytics, User Behavior Modeling, … WebSep 3, 2024 · Abstract: Recently, contrastive learning has been applied to the sequential recommendation task to address data sparsity caused by users with … WebDec 22, 2024 · The learning paradigm of SCL applies a multi-task learning strategy to jointly optimize the recommendation task loss(BPR loss, formula (5)) and the supervised contrastive loss(S-InfoNCE loss, formula (11)): (12) L = L B P R + λ 1 L S − I n f o N C E + λ 2 L 2 where λ 1 is the hyperparameters to control the strengths of S-InfoNCE. brave bear cubs