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

TL;DR

This paper introduces a boundary-aware multi-behavior dynamic graph transformer that models evolving user preferences by dynamically refining graph structures and capturing multiple behavior boundaries, leading to improved sequential recommendation accuracy.

Contribution

The paper proposes a novel dynamic graph transformer with boundary-aware multi-behavior modeling, addressing limitations of previous methods in capturing evolving user behaviors and graph structures.

Findings

Consistently outperforms baseline models on three datasets.

Effectively captures user behavior boundaries and dynamic preferences.

Enhances recommendation accuracy through boundary-aware optimization.

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.