Reproduce “Frequency-aware Graph Signal Processing for Collaborative Filtering” 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

Jiafeng Xia, Dongsheng Li, Hansu Gu, Tun Lu, Peng Zhang, Li Shang, Ning Gu

FaGSP predicts likely next items from user histories by selecting and boosting potentially distinctive past interactions, then smoothing the enhanced signal. It also applies separate filters across item and user neighborhoods to include indirect relations. In offline Top-K tests on six datasets, it leads every reported metric; on MovieLens 1M, F1@10 is 0.2203 versus GF-CF’s 0.2106. This is limited to these datasets and protocol.

Summary by alphaXiv.

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