Graph bottlenecked social recommendation

Y Yang, L Wu, Z Wang, Z He, R Hong… - Proceedings of the 30th …, 2024 - dl.acm.org
With the emergence of social networks, social recommendation has become an essential
technique for personalized services. Recently, graph-based social recommendations have …

Contextual Distillation Model for Diversified Recommendation

F Li, X Si, S Tang, D Wang, K Han, B Han… - Proceedings of the 30th …, 2024 - dl.acm.org
The diversity of recommendation is equally crucial as accuracy in improving user
experience. Existing studies, eg, Determinantal Point Process (DPP) and Maximal Marginal …

Popularity-aware alignment and contrast for mitigating popularity bias

M Cai, L Chen, Y Wang, H Bai, P Sun, L Wu… - Proceedings of the 30th …, 2024 - dl.acm.org
Collaborative Filtering~(CF) typically suffers from the significant challenge of popularity bias
due to the uneven distribution of items in real-world datasets. This bias leads to a significant …

Llm4dsr: Leveraing large language model for denoising sequential recommendation

B Wang, F Liu, J Chen, Y Wu, X Lou, J Wang… - ar** Matters: An Unsupervised Alignment enhanced Cross-Domain Cold-Start Recommendation
Z Wang, Y Yang, L Wu, R Hong… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Cold-start recommendation is a long-standing challenge when presenting potential
preferred items to new users. Most empirical studies leverage side information to promote …

Boosting Multimedia Recommendation via Separate Generic and Unique Awareness

Z He, Z Wang, Y Yang, H Bai, L Wu - arxiv preprint arxiv:2406.08270, 2024 - arxiv.org
Multimedia recommendation, which incorporates various modalities (eg, images, texts, etc.)
into user or item representation to improve recommendation quality, has received …

Personalized Denoising Implicit Feedback for Robust Recommender System

K Zhang, Q Cao, Y Wu, F Sun, H Shen… - arxiv preprint arxiv …, 2025 - arxiv.org
While implicit feedback is foundational to modern recommender systems, factors such as
human error, uncertainty, and ambiguity in user behavior inevitably introduce significant …

When SparseMoE Meets Noisy Interactions: An Ensemble View on Denoising Recommendation

W Chen, Z He, F Liu - arxiv preprint arxiv:2409.12730, 2024 - arxiv.org
Learning user preferences from implicit feedback is one of the core challenges in
recommendation. The difficulty lies in the potential noise within implicit feedback. Therefore …

Model-Agnostic Social Network Refinement with Diffusion Models for Robust Social Recommendation

Y Sun, Z Sun, Y Du, J Zhang, YS Ong - THE WEB CONFERENCE 2025 - openreview.net
Social recommendations (SRs) aim to enhance preference modeling by integrating social
networks. However, their effectiveness is mainly constrained by two factors: the noisy social …