GrIT: Group Informed Transformer for Sequential Recommendation

2026-02-23

AI Summary

This work addresses the limitation of existing sequential recommendation methods, which often overlook dynamic group-level behaviors and thus struggle to accurately capture the evolution of user interests. To this end, we propose a dynamic group representation mechanism that jointly models individual and group temporal preferences within a Transformer architecture. By introducing learnable time-varying group membership weights, our approach effectively integrates users’ short- and long-term behavioral patterns and explicitly captures the dynamic drift of group influence over time. Notably, this is the first effort to incorporate time-varying group modeling into sequential recommendation, combining group embeddings with behavioral statistical features. Extensive experiments on five benchmark datasets demonstrate that the proposed model significantly outperforms state-of-the-art methods, confirming the effectiveness of dynamic group information in enhancing recommendation performance.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Sequential recommender systems aim to predict a user's future interests by extracting temporal patterns from their behavioral history. Existing approaches typically employ transformer-based architectures to process long sequences of user interactions, capturing preference shifts by modeling temporal relationships between items. However, these methods often overlook the influence of group-level features that capture the collective behavior of similar users. We hypothesize that explicitly modeling temporally evolving group features alongside individual user histories can significantly enhance next-item recommendation. Our approach introduces latent group representations, where each user's affiliation to these groups is modeled through learnable, time-varying membership weights. The membership weights at each timestep are computed by modeling shifts in user preferences through their interaction history, where we incorporate both short-term and long-term user preferences. We extract a set of statistical features that capture the dynamics of user behavior and further refine them through a series of transformations to produce the final drift-aware membership weights. A group-based representation is derived by weighting latent group embeddings with the learned membership scores. This representation is integrated with the user's sequential representation within the transformer block to jointly capture personal and group-level temporal dynamics, producing richer embeddings that lead to more accurate, context-aware recommendations. We validate the effectiveness of our approach through extensive experiments on five benchmark datasets, where it consistently outperforms state-of-the-art sequential recommendation methods.

Problem

• sequential recommendation
• group-level features
• temporal dynamics
• user behavior modeling
• next-item prediction

Innovation

• Group-aware recommendation
• Temporal dynamics
• Latent group representation
• Time-varying membership
• Transformer-based sequential recommendation