Reproduce “T-RoPE: Time-Aware Rotary Position Embedding for 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
Yang Liu, Noel Loo, Ali Khanafer, Shuying Sun, Akshay Soni, Zhong Wu, Linjun Yang
T-RoPE adapts rotary attention for sequential recommendation by using event timestamps rather than sequence positions and reversing the key’s rotation so attention can respond to calendar phase as well as elapsed time. On Amazon Books, HSTU + T-RoPE reaches 7.65% HR@10 versus 6.89% with Time RAB, an 11.0% relative gain; this does not establish seasonality as its cause.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.