8 papers
DrEM: Dual-Side Robust Ensemble Ranking from Noisy User Preference Predictions in Video Recommendation
Canwei Huang, Tiantian He, Xiaoxiao Xu +5
Industrial video recommendation systems typically adopt a multi-stage architecture. At the ensemble ranking stage, multi-dimensional user preference predictions (pxtrs) from an ups…
Behavior-Aware Dual-Channel Preference Learning for Heterogeneous Sequential Recommendation
Jing Xiao, Dongqi Wu, Liwei Pan +3
Heterogeneous sequential recommendation (HSR) aims to learn dynamic behavior dependencies from the diverse behaviors of user-item interactions to facilitate precise sequential reco…
The Double-Edged Sword of Knowledge Transfer: Diagnosing and Curing Fairness Pathologies in Cross-Domain Recommendation
Yuhan Zhao, Weixin Chen, Li Chen +1
Cross-domain recommendation (CDR) offers an effective strategy for improving recommendation quality in a target domain by leveraging auxiliary signals from source domains. Nonethel…
Towards Multi-Behavior Multi-Task Recommendation via Behavior-informed Graph Embedding Learning
Wenhao Lai, Weike Pan, Zhong Ming
Multi-behavior recommendation (MBR) aims to improve the performance w.r.t. the target behavior (i.e., purchase) by leveraging auxiliary behaviors (e.g., click, favourite). However,…
Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
Donglin Zhou, Weike Pan, Zhong Ming
Sequential recommendation (SR) models often capture user preferences based on the historically interacted item IDs, which usually obtain sub-optimal performance when the interactio…
Leave No One Behind: Fairness-Aware Cross-Domain Recommender Systems for Non-Overlapping Users
Weixin Chen, Yuhan Zhao, Li Chen +1
Cross-domain recommendation (CDR) methods predominantly leverage overlapping users to transfer knowledge from a source domain to a target domain. However, through empirical studies…