TME-PSR: Time-aware, Multi-interest, and Explanation Personalization for Sequential Recommendation

2026-04-10

AI Summary

This work addresses key limitations in sequential recommendation—namely, the neglect of user-specific temporal rhythms, insufficient modeling of multi-interest dynamics, and semantic misalignment between recommendations and their explanations—by proposing a unified framework that integrates time-awareness, fine-grained multi-interest representation, and explainability. The framework incorporates a dual-view gated temporal encoder, a lightweight multi-head linear recurrent unit, and a dynamic dual-branch mutual information weighting mechanism. Evaluated on real-world datasets, the proposed approach significantly enhances both recommendation accuracy and explanation quality while substantially reducing computational overhead.

Technology Category

• Reasoning under Uncertainty: Sequential Decision Making
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

In this paper, we propose a sequential recommendation model that integrates Time-aware personalization, Multi-interest personalization, and Explanation personalization for Personalized Sequential Recommendation (TME-PSR). That is, we consider the differences across different users in temporal rhythm preference, multiple fine-grained latent interests, and the personalized semantic alignment between recommendations and explanations. Specifically, the proposed TME-PSR model employs a dual-view gated time encoder to capture personalized temporal rhythms, a lightweight multihead Linear Recurrent Unit architecture that enables fine-grained sub-interest modeling with improved efficiency, and a dynamic dual-branch mutual information weighting mechanism to achieve personalized alignment between recommendations and explanations. Extensive experiments on real-world datasets demonstrate that our method consistently improves recommendation accuracy and explanation quality, at a lower computational cost.

Problem

• sequential recommendation
• time-aware personalization
• multi-interest personalization
• explanation personalization

Innovation

• Time-aware Personalization
• Multi-interest Modeling
• Explanation Personalization
• Linear Recurrent Unit
• Mutual Information Weighting