MMHCL: Multi-Modal Hypergraph Contrastive Learning for Recommendation

2025-04-23

AI Summary

To address insufficient user-item semantic association learning caused by data sparsity and cold-start challenges in multimodal recommendation, this paper proposes the Multimodal Hypergraph Contrastive Learning (MHCL) framework. Methodologically: (1) it constructs dual hypergraphs—user-user and item-item—to explicitly model high-order semantic correlations; (2) it jointly encodes multimodal features by integrating first-order interaction signals with second-order hypergraph representations; and (3) it introduces a collaborative contrastive learning module that maximizes mutual information and minimizes noise interference on both user and item sides, jointly optimizing shared preference alignment and multimodal semantic similarity. Extensive experiments demonstrate that MHCL consistently outperforms state-of-the-art methods across multiple benchmark datasets, effectively mitigating both cold-start and data sparsity issues. The implementation is publicly available.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The burgeoning presence of multimodal content-sharing platforms propels the development of personalized recommender systems. Previous works usually suffer from data sparsity and cold-start problems, and may fail to adequately explore semantic user-product associations from multimodal data. To address these issues, we propose a novel Multi-Modal Hypergraph Contrastive Learning (MMHCL) framework for user recommendation. For a comprehensive information exploration from user-product relations, we construct two hypergraphs, i.e. a user-to-user (u2u) hypergraph and an item-to-item (i2i) hypergraph, to mine shared preferences among users and intricate multimodal semantic resemblance among items, respectively. This process yields denser second-order semantics that are fused with first-order user-item interaction as complementary to alleviate the data sparsity issue. Then, we design a contrastive feature enhancement paradigm by applying synergistic contrastive learning. By maximizing/minimizing the mutual information between second-order (e.g. shared preference pattern for users) and first-order (information of selected items for users) embeddings of the same/different users and items, the feature distinguishability can be effectively enhanced. Compared with using sparse primary user-item interaction only, our MMHCL obtains denser second-order hypergraphs and excavates more abundant shared attributes to explore the user-product associations, which to a certain extent alleviates the problems of data sparsity and cold-start. Extensive experiments have comprehensively demonstrated the effectiveness of our method. Our code is publicly available at: https://github.com/Xu107/MMHCL.

Problem

• Addresses data sparsity in multimodal recommender systems
• Explores semantic user-product associations from multimodal data
• Alleviates cold-start problems via hypergraph contrastive learning

Innovation

• Constructs user-user and item-item hypergraphs
• Uses contrastive learning for feature enhancement
• Fuses first-order and second-order semantic information