@Misc{HaoWu2023,
author="Hao Wu
and Alejandro Ariza-Casabona
and Bart{\l}omiej Twardowski
and Tri Kurniawan Wijaya",
title="MM-GEF: Multi-modal representation meet collaborative filtering",
year="2023",
abstract="In modern e-commerce, item content features in various modalities offer accurate yet comprehensive information to recommender systems. The majority of previous work either focuses on learning effective item representation during modelling user-item interactions, or exploring item-item relationships by analysing multi-modal features. Those methods, however, fail to incorporate the collaborative item-user-item relationships into the multi-modal feature-based item structure. In this work, we propose a graph-based item structure enhancement method MM-GEF: Multi-Modal recommendation with Graph Early-Fusion, which effectively combines the latent item structure underlying multi-modal contents with the collaborative signals. Instead of processing the content feature in different modalities separately, we show that the early-fusion of multi-modal features provides significant improvement. MM-GEF learns refined item representations by injecting structural information obtained from both multi-modal and collaborative signals. Through extensive experiments on four publicly available datasets, we demonstrate systematical improvements of our method over state-of-the-art multi-modal recommendation methods.",
optnote="LAMP",
optnote="exported from refbase (http://158.109.8.37/show.php?record=3988), last updated on Tue, 30 Jan 2024 15:40:53 +0100",
opturl="https://arxiv.org/abs/2308.07222",
file=":http://158.109.8.37/files/WAT2023.pdf:PDF"
}