Boundary-Aware Multi-Behavior Dynamic Graph Transformer for Sequential Recommendation

2026-02-11

AI Summary

Existing methods struggle to simultaneously capture the dynamics of user behavior sequences, the evolution of graph structures, and the interest boundaries across multiple types of interactions, leading to inadequate user preference modeling. To address this limitation, this work proposes a boundary-aware multi-behavior dynamic graph Transformer model that explicitly distinguishes interest boundaries among different behaviors. The model dynamically updates the user–item interaction graph, integrates temporal behavior sequences, and introduces a user-specific multi-behavior loss function. By combining a Transformer-based dynamic graph aggregator with a multi-behavior optimization mechanism, the proposed approach significantly outperforms state-of-the-art methods on three public datasets, demonstrating its effectiveness and superiority in sequential recommendation tasks.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Humans and AI: Human-Aware Planning and Behavior Prediction
• 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
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In the landscape of contemporary recommender systems, user-item interactions are inherently dynamic and sequential, often characterized by various behaviors. Prior research has explored the modeling of user preferences through sequential interactions and the user-item interaction graph, utilizing advanced techniques such as graph neural networks and transformer-based architectures. However, these methods typically fall short in simultaneously accounting for the dynamic nature of graph topologies and the sequential pattern of interactions in user preference models. Moreover, they often fail to adequately capture the multiple user behavior boundaries during model optimization. To tackle these challenges, we introduce a boundary-aware Multi-Behavioral Dynamic Graph Transformer (MB-DGT) model that dynamically refines the graph structure to reflect the evolving patterns of user behaviors and interactions. Our model involves a transformer-based dynamic graph aggregator for user preference modeling, which assimilates the changing graph structure and the sequence of user behaviors. This integration yields a more comprehensive and dynamic representation of user preferences. For model optimization, we implement a user-specific multi-behavior loss function that delineates the interest boundaries among different behaviors, thereby enriching the personalized learning of user preferences. Comprehensive experiments across three datasets indicate that our model consistently delivers remarkable recommendation performance.

Problem

• sequential recommendation
• dynamic graph
• multi-behavior
• user preference modeling
• behavior boundary

Innovation

• Dynamic Graph Transformer
• Multi-Behavior Recommendation
• Boundary-Aware Learning
• Sequential Recommendation
• User Preference Modeling