Multi-behavior sequential recommendation systems, which predict users' subsequent interactions based on historical behavior sequences, play a vital role in e-commerce operations. Despite the promising results of existing state-of-the-art methods, which employ either advanced attention mechanisms or graph-based neural networks, they still face a few open challenges, including the diversity of user actions, the intricate relationships within time-evolving interactions, and the complications introduced by limited or noisy data. To address these limitations, we propose a Similarity Graph-enhanced Multi-Scale Transformer (SG-MST) for multi-behavior e-commerce product recommendation. SG-MST integrates a Similarity Augmented Multi-Behavior Hypergraph that captures complex behavior-aware dependencies among items and strengthens connections through item context similarities, producing more informative latent representations. Additionally, we introduce a Contrastively Regularized Multi-Scale Transformer, which leverages contrastive learning to capture enriched sequential patterns across both long-term and short-term dynamically sampled and augmented temporal scales, thereby improving the robustness of user behavior prediction. Extensive evaluation on three real-world benchmark datasets demonstrates that the proposed SG-MST outperforms other state-of-the-art methods.

ICMR '24: International Conference on Multimedia Retrieval, Phuket, Thailand, June 10-14, 2024

Fashion recommendation considers both product similarity and compatibility, and has drawn increasing research interest. It is a challenging task because it often needs to use information from different sources, such as visual content or textual descriptions for the prediction of user preferences. In terms of complementary recommendation, existing approaches were dedicated to modeling either product compatibility or users’ personalization in a direct and decoupled manner, yet overlooked additional relations hidden within historical user-product interactions. In this paper, we propose a Normalized indirect Personal Compatibility modeling scheme based on Bayesian Personalized Ranking (NiPC-BPR) for mix-and-match clothing recommendations. We exploit direct and indirect personalization and compatibility relations from the user and product interactions, and effectively integrate various multi-modal data. Extensive experimental results on two benchmark datasets show that our method outperforms other methods by large margins.