Reproduce “Integrating Large Language Models with Graphical Session-Based 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
Naicheng Guo, Hongwei Cheng, Qianqiao Liang, Linxun Chen, Bing Han
LLMGR adapts a language model for session-based recommendation by connecting item text, item IDs, and session-graph structure. It first trains auxiliary tasks to align text with graph nodes and learn successor relationships, then tunes the model to score candidate next items. On Beauty, it reaches 0.7501 HitRate@20 versus 0.6677 for HCGR, under sampled-candidate evaluation rather than full-catalog ranking.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.