i$^2$VAE: Interest Information Augmentation with Variational Regularizers for Cross-Domain Sequential Recommendation

2024-05-31

AI Summary

To address the insufficient modeling of non-overlapping cold-start and long-tail users in cross-domain sequential recommendation (CDSR), this paper proposes i²VAE, a variational autoencoder-based framework. It introduces a novel dual mutual information regularization strategy—jointly enforcing cross-domain alignment and disentangled representation learning—to enable robust user interest transfer. Additionally, it integrates pseudo-interaction sequence generation with denoising reconstruction to explicitly capture latent preferences under sparse behavioral signals. To our knowledge, i²VAE is the first method to jointly optimize recommendations for both non-overlapping cold-start and long-tail users. Extensive experiments on multiple real-world cross-domain datasets demonstrate state-of-the-art performance: Recall@10 improves by 18.7% for cold-start users, and NDCG@10 increases by 22.3% for long-tail users.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Reasoning under Uncertainty: Sequential Decision Making
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Cross-Domain Sequential Recommendation (CDSR) leverages user behaviors across multiple domains to mitigate data sparsity and cold-start challenges in Single-Domain Sequential Recommendation. Existing methods primarily rely on shared users (overlapping users) to learn transferable interest representations. However, these approaches have limited information propagation, benefiting mainly overlapping users and those with rich interaction histories while neglecting non-overlapping (cold-start) and long-tailed users, who constitute the majority in real-world scenarios. To address this issue, we propose i$^2$VAE, a novel variational autoencoder (VAE)-based framework that enhances user interest learning with mutual information-based regularizers. i$^2$VAE improves recommendations for cold-start and long-tailed users while maintaining strong performance across all user groups. Specifically, cross-domain and disentangling regularizers extract transferable features for cold-start users, while a pseudo-sequence generator synthesizes interactions for long-tailed users, refined by a denoising regularizer to filter noise and preserve meaningful interest signals. Extensive experiments demonstrate that i$^2$VAE outperforms state-of-the-art methods, underscoring its effectiveness in real-world CDSR applications.

Problem

• Enhances cross-domain recommendations for cold-start users
• Improves recommendations for long-tailed user groups
• Addresses data sparsity in sequential recommendation systems

Innovation

• VAE-based framework with mutual information regularizers
• Cross-domain and disentangling regularizers for cold-start users
• Pseudo-sequence generator with denoising for long-tailed users