The Best is Yet to Come: Graph Convolution in the Testing Phase for Multimodal Recommendation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Jinfeng, Chen, Zheyu, Yang, Shuo, Li, Jinze, Ngai, Edith C. H.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911075065135104
author Xu, Jinfeng
Chen, Zheyu
Yang, Shuo
Li, Jinze
Ngai, Edith C. H.
author_facet Xu, Jinfeng
Chen, Zheyu
Yang, Shuo
Li, Jinze
Ngai, Edith C. H.
contents The efficiency and scalability of graph convolution networks (GCNs) in training recommender systems remain critical challenges, hindering their practical deployment in real-world scenarios. In the multimodal recommendation (MMRec) field, training GCNs requires more expensive time and space costs and exacerbates the gap between different modalities, resulting in sub-optimal recommendation accuracy. This paper critically points out the inherent challenges associated with adopting GCNs during the training phase in MMRec, revealing that GCNs inevitably create unhelpful and even harmful pairs during model optimization and isolate different modalities. To this end, we propose FastMMRec, a highly efficient multimodal recommendation framework that deploys graph convolutions exclusively during the testing phase, bypassing their use in training. We demonstrate that adopting GCNs solely in the testing phase significantly improves the model's efficiency and scalability while alleviating the modality isolation problem often caused by using GCNs during the training phase. We conduct extensive experiments on three public datasets, consistently demonstrating the performance superiority of FastMMRec over competitive baselines while achieving efficiency and scalability.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18489
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Best is Yet to Come: Graph Convolution in the Testing Phase for Multimodal Recommendation
Xu, Jinfeng
Chen, Zheyu
Yang, Shuo
Li, Jinze
Ngai, Edith C. H.
Information Retrieval
The efficiency and scalability of graph convolution networks (GCNs) in training recommender systems remain critical challenges, hindering their practical deployment in real-world scenarios. In the multimodal recommendation (MMRec) field, training GCNs requires more expensive time and space costs and exacerbates the gap between different modalities, resulting in sub-optimal recommendation accuracy. This paper critically points out the inherent challenges associated with adopting GCNs during the training phase in MMRec, revealing that GCNs inevitably create unhelpful and even harmful pairs during model optimization and isolate different modalities. To this end, we propose FastMMRec, a highly efficient multimodal recommendation framework that deploys graph convolutions exclusively during the testing phase, bypassing their use in training. We demonstrate that adopting GCNs solely in the testing phase significantly improves the model's efficiency and scalability while alleviating the modality isolation problem often caused by using GCNs during the training phase. We conduct extensive experiments on three public datasets, consistently demonstrating the performance superiority of FastMMRec over competitive baselines while achieving efficiency and scalability.
title The Best is Yet to Come: Graph Convolution in the Testing Phase for Multimodal Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2507.18489