Reproduce “MuSeR: Scalable Long-sequence Recommendation with Multi-interest Modeling” 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
Yongkang Fu, Beining Bao, Yu Jiang, Xiangyu Zhao, Hongyang Wei, Guangxing Chen, Zuodong Yang, Shantao Li and 5 more
MuSeR addresses long-history recommendation by retaining recent behavior in detail, compressing older interactions at multiple temporal scales, and representing users with several candidate-aware interests. It adds item-content semantics and asynchronously caches long-term representations for retrieval. In a Baidu APP homepage-feed A/B test, feed DAU rose 0.26% and session duration 0.89%, but the test evaluates the integrated retrieval channel.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.