M^2VAE: Multi-Modal Multi-View Variational Autoencoder for Cold-start Item Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Chuan, Liu, Yongchao, Li, Qiang, Zhong, Wenliang, Hong, Chuntao, Yao, Xinwei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915612521922560
author He, Chuan
Liu, Yongchao
Li, Qiang
Zhong, Wenliang
Hong, Chuntao
Yao, Xinwei
author_facet He, Chuan
Liu, Yongchao
Li, Qiang
Zhong, Wenliang
Hong, Chuntao
Yao, Xinwei
contents 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, the distinction between shared and modality-specific features. In this paper, we propose Multi-Modal Multi-View Variational AutoEncoder (M^2VAE), 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 preference-guided 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00452
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle M^2VAE: Multi-Modal Multi-View Variational Autoencoder for Cold-start Item Recommendation
He, Chuan
Liu, Yongchao
Li, Qiang
Zhong, Wenliang
Hong, Chuntao
Yao, Xinwei
Information Retrieval
Artificial Intelligence
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, the distinction between shared and modality-specific features. In this paper, we propose Multi-Modal Multi-View Variational AutoEncoder (M^2VAE), 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 preference-guided 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.
title M^2VAE: Multi-Modal Multi-View Variational Autoencoder for Cold-start Item Recommendation
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2508.00452