What type of study is this?

Semantic Relation Guided Dual-view Contrastive Learning for Session-based Recommendations

View Full Paper

Ask AI

Bookmark

Authors

Proposed framework improves next-item prediction by addressing user intent and item attributes, highlighting significant performance gains.

The proposed SCL-SR significantly enhances recommendation performance by integrating user intent and item attributes.
Experiments on three real-world datasets demonstrate performance improvements ranging from 7.10% to 12.82% over state-of-the-art methods.
This framework utilizes a semantic relation-guided contrastive learning module to refine next-item predictions effectively.
An intent-attribute disentangler reduces interference between user intent and item characteristics, optimizing recommendation accuracy.

Zhang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

Proposed framework improves next-item prediction by addressing user intent and item attributes, highlighting significant performance gains.