M²VAE: Multi-Modal Multi-View Variational Autoencoder for Cold-start Item Recommendation

Cold-start item recommendation is a significant challenge in recommendation systems, particularly when new items are introduced without any historical interaction data. While existing methods leverage multi-modal content to alleviate the cold-start issue, they often neglect the inherent multi-view structure of modalities, namely the distinction between shared and modality-specific features. In this paper, we propose Multi-Modal Multi-View Variational AutoEncoder (M²VAE), a generative model that addresses the challenges of modeling common and unique views in attribute and multi-modal features, as well as user preferences over single-typed item features. Specifically, we generate type-specific latent variables for item IDs, categorical attributes, and image features, and use Product-of-Experts (PoE) to derive a common representation. A disentangled contrastive loss decouples the common view from unique views while preserving feature informativeness. To model user inclinations, we employ a user-aware hierarchical Mixture-of-Experts (MoE) to adaptively fuse representations. We further incorporate co-occurrence signals via contrastive learning, eliminating the need for pretraining. Extensive experiments on real-world datasets validate the effectiveness of our approach.

Authors

• Chuan He Zhejiang University of Technology Ant Group
• Yongchao Liu Ant Group
• Qiang Li Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology
• Chuntao Hong Ant Group
• Wenliang Zhong
• Xin-Wei Yao Zhejiang University of Technology

Keywords

No keywords are indexed for this paper.