Contrastive Modality-Disentangled Learning for Multimodal Recommendation
ACM Transactions on Information Systems · 31.05.2025 · 43 (3) · 1-31
DOI: 10.1145/3715876 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 15.03.2025. Verfasst von Xixun Lin und 8 weiteren Autor:innen. Die Arbeit wurde bisher 53-mal zitiert (Crossref) und nennt 108 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, CCF-ALIMAMA TECH Kangaroo.
Abstract (Originalsprache)
Multimodal recommendation, which utilizes rich multimodal information to learn user preferences, has attracted significant attention. Most works focus on designing powerful encoders for extracting multimodal features, and simply aggregate the learned features together to make prediction. Consequently, they have a limited capacity to learn the inter-modality knowledge including the modality-shared and modality-unique knowledge. In fact, learning the modality-shared knowledge enables us to align cross-modality data for fusing heterogeneous modality features. Learning the modality-unique knowledge is equally important when recommendation tasks only involve a small amount of shared features and the necessary information is contained within specific modality. In this article, we propose Contrastive Modality-Disentangled Learning (CMDL) to overcome this critical limitation. CMDL exactly captures the inter-modality knowledge by achieving modality disentanglement. Specifically, CMDL first disentangles the initial representation into the modality-invariant and modality-specific representations. Afterwards, CMDL introduces a novel manner of contrastive learning to approximate the MI upper bounds for achieving disentanglement regularization. Building upon the proposed regularization, CMDL encourages the modality-invariant and modality-specific representations to capture the modality-shared and modality-unique knowledge respectively and to be statistically independent to each other. Empirically, extensive experiments are conducted on benchmark datasets, demonstrating the superior performance of CMDL compared with strong multimodal recommenders.
Förderung
- National Natural Science Foundation of China
- CCF-ALIMAMA TECH Kangaroo
Zitieren
APA
Lin, X., Liu, R., Cao, Y., Zou, L., Li, Q., Wu, Y., Liu, Y., Yin, D., & Xu, G. (2025). Contrastive Modality-Disentangled Learning for Multimodal Recommendation. ACM Transactions on Information Systems, 43(3), 1-31. https://doi.org/10.1145/3715876
Vancouver
Lin X, Liu R, Cao Y, Zou L, Li Q, Wu Y, et al. Contrastive Modality-Disentangled Learning for Multimodal Recommendation. ACM Transactions on Information Systems. 2025;43(3):1-31. doi:10.1145/3715876
BibTeX
@article{Lin2025,
author = {Lin, Xixun and Liu, Rui and Cao, Yanan and Zou, Lixin and Li, Qian and Wu, Yongxuan and Liu, Yang and Yin, Dawei and Xu, Guandong},
title = {Contrastive Modality-Disentangled Learning for Multimodal Recommendation},
journal = {ACM Transactions on Information Systems},
year = {2025},
volume = {43},
number = {3},
pages = {1--31},
doi = {10.1145/3715876}
}
EUVIMED