RoTE: Coarse-to-Fine Multi-Level Rotary Time Embedding for Sequential Recommendation

2026-04-14

AI Summary

This work addresses the limitation of existing sequential recommendation methods, which rely solely on interaction order while neglecting temporal intervals, thereby struggling to accurately capture the evolution of users’ short- and long-term interests. To overcome this, the authors propose RoTE (Rotary Time Encoding), a lightweight and plug-and-play module that decomposes timestamps into multi-granularity representations and explicitly incorporates temporal spans between interactions into item embeddings via a rotation mechanism. RoTE seamlessly integrates with Transformer-based architectures without requiring modifications to the backbone model, enabling fine-grained awareness of heterogeneous temporal patterns. Extensive experiments on three public benchmarks demonstrate that RoTE consistently enhances the performance of state-of-the-art models, achieving up to a 20.11% relative improvement in NDCG@5, thereby validating its effectiveness and generalizability.

Technology Category

• Planning, Routing, and Scheduling: Temporal Planning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

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 considers the order of temporal information but overlooks the actual time spans between interactions, resulting in a coarse representation of users' temporal dynamics and limiting the model's ability to capture long-term and short-term interest evolution. To address this limitation, we propose RoTE, a novel multi-level temporal embedding module that explicitly models time span information in sequential recommendation. RoTE decomposes each interaction timestamp into multiple temporal granularities, ranging from coarse to fine, and incorporates the resulting temporal representations into item embeddings. This design enables models to capture heterogeneous temporal patterns and better perceive temporal distances among user interactions during sequence modeling. RoTE is a lightweight, plug-and-play module that can be seamlessly integrated into existing Transformer-based sequential recommendation models without modifying their backbone architectures. We apply RoTE to several representative models and conduct extensive experiments on three public benchmarks. Experimental results demonstrate that RoTE consistently enhances the corresponding backbone models, achieving up to a 20.11% improvement in NDCG@5, which confirms the effectiveness and generality of the proposed approach. Our code is available at https://github.com/XiaoLongtaoo/RoTE.

Problem

• sequential recommendation
• temporal dynamics
• time span
• user behavior modeling
• interest evolution

Innovation

• Rotary Time Embedding
• Sequential Recommendation
• Temporal Granularity
• Time Span Modeling
• Plug-and-Play Module