activity
20182023
most citedMulti-Behavior Recommendation with Cascading Graph Convolution Networks

108 citations · 134 across the 14 of their papers we have counts for

collaborators

29 papers

cs.IR2023★ 2 cited

Semantic-Guided Feature Distillation for Multimodal Recommendation

Fan Liu, Huilin Chen, Zhiyong Cheng +2

Multimodal recommendation exploits the rich multimodal information associated with users or items to enhance the representation learning for better performance. In these methods, e…

cs.CV2023

Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration

Harry Cheng, Yangyang Guo, Liqiang Nie +2

Training an effective video action recognition model poses significant computational challenges, particularly under limited resource budgets. Current methods primarily aim to eithe…

cs.IR2023★ 4 cited

Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community

Qingyao Ai, Ting Bai, Zhao Cao +30

The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs. Recently, Large Language Mod…

cs.IR2023★ 8 cited

MB-HGCN: A Hierarchical Graph Convolutional Network for Multi-behavior Recommendation

Mingshi Yan, Zhiyong Cheng, Jing Sun +2

Collaborative filtering-based recommender systems that rely on a single type of behavior often encounter serious sparsity issues in real-world applications, leading to unsatisfacto…

cs.IR2023★ 108 cited

Multi-Behavior Recommendation with Cascading Graph Convolution Networks

Zhiyong Cheng, Sai Han, Fan Liu +3

Multi-behavior recommendation, which exploits auxiliary behaviors (e.g., click and cart) to help predict users' potential interactions on the target behavior (e.g., buy), is regard…

cs.IR2022★ 1 cited

Privacy-Preserving Synthetic Data Generation for Recommendation Systems

Fan Liu, Zhiyong Cheng, Huilin Chen +3

Recommendation systems make predictions chiefly based on users' historical interaction data (e.g., items previously clicked or purchased). There is a risk of privacy leakage when c…