MMGRec: Multimodal Generative Recommendation with Transformer Model
ACM Transactions on Multimedia Computing, Communications, and Applications · 31.10.2026 · 22 (10) · 1-21
DOI: 10.1145/3838594 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 08.10.2026. Verfasst von Han Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Guangdong S&T Program, Key R&D Program of Shandong Province, China.
Abstract (Originalsprache)
Multimodal recommendation aims to recommend user-preferred candidates based on her/his historically interacted items and associated multimodal information. Previous studies commonly employ an embed-and-retrieve paradigm: learning user and item representations in the same embedding space, then retrieving similar candidate items for a user via embedding inner product. However, this paradigm suffers from inference cost, interaction modeling, and false-negative issues. Toward this end, we propose a new MMGRec model to introduce a generative paradigm into multimodal recommendation. Specifically, we first devise a hierarchical quantization method Graph RQ-VAE to assign a Rec-ID for each item from its multimodal and CF information. Consisting of a tuple of semantically meaningful tokens, Rec-ID serves as the unique identifier of each item. Afterward, we train a Transformer-based recommender to generate the Rec-IDs of user-preferred items based on historical interaction sequences. The generative paradigm is qualified since this model systematically predicts the tuple of tokens identifying the recommended item in an autoregressive manner. Moreover, a relation-aware self-attention mechanism is devised for the Transformer to handle non-sequential interaction sequences, which explores the element–pairwise relation to replace absolute positional encoding. Extensive experiments evaluate MMGRec’s effectiveness compared with state-of-the-art methods.
Förderung
- National Natural Science Foundation of China
- Guangdong S&T Program
- Key R&D Program of Shandong Province, China
- NSFC
- Guangdong Basic and Applied Basic Research Foundation
Zitieren
APA
Liu, H., Wei, Y., Song, X., Guan, W., Li, Y., & Nie, L. (2026). MMGRec: Multimodal Generative Recommendation with Transformer Model. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(10), 1-21. https://doi.org/10.1145/3838594
Vancouver
Liu H, Wei Y, Song X, Guan W, Li Y, Nie L. MMGRec: Multimodal Generative Recommendation with Transformer Model. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(10):1-21. doi:10.1145/3838594
BibTeX
@article{Liu2026,
author = {Liu, Han and Wei, Yinwei and Song, Xuemeng and Guan, Weili and Li, Yuan-Fang and Nie, Liqiang},
title = {MMGRec: Multimodal Generative Recommendation with Transformer Model},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2026},
volume = {22},
number = {10},
pages = {1--21},
doi = {10.1145/3838594}
}
EUVIMED