Reproduce “LogicRec: Recommendation with Users' Logical Requirements” 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
Zhenwei Tang, Griffin Floto, Armin Toroghi, Shichao Pei, Xiangliang Zhang, Scott Sanner
LogicRec formulates recommendation as the intersection of preference and logical-requirement queries over a knowledge graph. Built on GQE, it embeds queries and items to score answers despite missing links, while sharing representations across three retrieval tasks. On Amazon-book 3i it achieves 0.345 hit@20 versus BetaE’s 0.302 averaged over three runs; gains occur on most, not all, query types.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.