Reproduce “APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Mingjia Yin, Hao Wang, Xiang Xu, Likang Wu, Sirui Zhao, Wei Guo, Yong Liu, Ruiming Tang and 2 more

APGL4SR learns a refined global item graph from users’ interaction sequences and uses each user’s history to modulate graph-derived relationships in sequence attention. On Beauty, it reports NDCG@20 of 0.0527 ± 0.0006, compared with 0.0480 ± 0.0006 for ICLRec (p < 0.001). It leads reported HR and NDCG metrics across four datasets in offline evaluation, not deployment.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.