1

Collaborative Alignment for Recommendation

Traditional recommender systems have primarily relied on identity representations (IDs) to model users and items. Recently, the …

Chen Wang, Liangwei Yang, Zhiwei Liu, Xiaolong Liu, Mingdai Yang, Yueqing Liang, Philip S. Yu

Do We Really Need Graph Convolution During Training? Light Post-Training Graph-ODE for Efficient Recommendation

The efficiency and scalability of graph convolution networks (GCNs) in training recommender systems (RecSys) have been persistent …

Weizhi Zhang, Liangwei Yang, Zihe Song, Henry Peng Zhou, Ke Xu, Liancheng Fang, Philip S. Yu

Pre-Training with Transferable Attention for Addressing Market Shifts in Cross-Market Sequential Recommendation

Cross-market recommendation (CMR) involves selling the same set of items across multiple nations or regions within a transfer learning …

Chen Wang, Ziwei Fan, Liangwei Yang, Mingdai Yang, Xiaolong Liu, Zhiwei Liu, Philip S. Yu

Instruction-based Hypergraph Pretraining

Pretraining has been widely explored to augment the adaptability of graph learning models to transfer knowledge from large datasets to …

Mingdai Yang, Zhiwei Liu, Liangwei Yang, Xiaolong Liu, Chen Wang, Hao Peng, Philip S. Yu

Conditional denoising diffusion for sequential recommendation

Contemporary attention-based sequential recommendations often encounter the oversmoothing problem, which generates indistinguishable …

Yu Wang, Zhiwei Liu, Liangwei Yang, Philip S. Yu

Knowledge Graph Context-Enhanced Diversified Recommendation

The field of Recommender Systems (RecSys) has been extensively studied to enhance accuracy by leveraging users’ historical …

Xiaolong Liu, Liangwei Yang, Zhiwei Liu, Mingdai Yang, Chen Wang, Hao Peng, Philip S. Yu

Unified Pretraining for Recommendation via Task Hypergraphsn

Although pretraining has garnered significant attention and popularity in recent years, its application in graph-based recommender …

Mingdai Yang, Zhiwei Liu, Liangwei Yang, Xiaolong Liu, Chen Wang, Hao Peng, Philip S. Yu

Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering

Collaborative filtering (CF) is a widely employed technique that predicts user preferences based on past interactions. Negative …

Xi Wu, Liangwei Yang, Jibing Gong, Chao Zhou, Tianyu Lin, Xiaolong Liu, Philip S. Yu

Dual-Teacher Knowledge Distillation for Strict Cold-Start Recommendation

Recommender systems (RecSys) aim to predict users’ preferences based on historical interactions and content profiles, and they are …

Weizhi Zhang, Liangwei Yang, Yuwei Cao, Ke Xu, Yuanjie Zhu, Philip S. Yu

Graph-based Alignment and Uniformity for Recommendation

Collaborative filtering-based recommender systems (RecSys) rely on learning representations for users and items to predict preferences …

Liangwei Yang, Zhiwei Liu, Chen Wang, Mingdai Yang, Xiaolong Liu, Jing Ma, Philip S. Yu