一作SIGIR 2026Poster· Information Retrieval (Short)
RoTE: Coarse-to-Fine Multi-Level Rotary Time Embedding for Sequential Recommendation
Haolin Zhang · Longtao Xiao · Guohao Cai · Ruixuan Li · Xiu Li
摘要
Sequential recommendation models have been widely adopted for modeling user behavior. Existing approaches typically construct user interaction sequences by sorting items according to timestamps and then model user preferences from historical behaviors. While effective, such a process only conside...