Enhancing Multimodal Recommendations with Vision-Language Models and Information-Aware Fusion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kieu, Hai-Dang, Xu, Min, Huynh, Thanh Trung, Le, Dung D.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912697425068032
author Kieu, Hai-Dang
Xu, Min
Huynh, Thanh Trung
Le, Dung D.
author_facet Kieu, Hai-Dang
Xu, Min
Huynh, Thanh Trung
Le, Dung D.
contents Recent advances in multimodal recommendation (MMR) highlight the potential of integrating visual and textual content to enrich item representations. However, existing methods often rely on coarse visual features and naive fusion strategies, resulting in redundant or misaligned representations. From an information-theoretic perspective, effective fusion should balance unique, shared, and redundant modality information to preserve complementary cues. To this end, we propose VIRAL, a novel Vision-Language and Information-aware Recommendation framework that enhances multimodal fusion through two components: (i) a VLM-based visual enrichment module that generates fine-grained, title-guided descriptions for semantically aligned image representations, and (ii) an information-aware fusion module inspired by Partial Information Decomposition (PID) to disentangle and integrate complementary signals. Experiments on three Amazon datasets show that VIRAL consistently outperforms strong multimodal baselines and substantially improves the contribution of visual features.
format Preprint
id arxiv_https___arxiv_org_abs_2511_02113
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Multimodal Recommendations with Vision-Language Models and Information-Aware Fusion
Kieu, Hai-Dang
Xu, Min
Huynh, Thanh Trung
Le, Dung D.
Information Retrieval
Recent advances in multimodal recommendation (MMR) highlight the potential of integrating visual and textual content to enrich item representations. However, existing methods often rely on coarse visual features and naive fusion strategies, resulting in redundant or misaligned representations. From an information-theoretic perspective, effective fusion should balance unique, shared, and redundant modality information to preserve complementary cues. To this end, we propose VIRAL, a novel Vision-Language and Information-aware Recommendation framework that enhances multimodal fusion through two components: (i) a VLM-based visual enrichment module that generates fine-grained, title-guided descriptions for semantically aligned image representations, and (ii) an information-aware fusion module inspired by Partial Information Decomposition (PID) to disentangle and integrate complementary signals. Experiments on three Amazon datasets show that VIRAL consistently outperforms strong multimodal baselines and substantially improves the contribution of visual features.
title Enhancing Multimodal Recommendations with Vision-Language Models and Information-Aware Fusion
topic Information Retrieval
url https://arxiv.org/abs/2511.02113