MM-GEF: Multi-modal representation meet collaborative filtering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Hao, Ariza-Casabona, Alejandro, Twardowski, Bartłomiej, Wijaya, Tri Kurniawan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914912516702208
author Wu, Hao
Ariza-Casabona, Alejandro
Twardowski, Bartłomiej
Wijaya, Tri Kurniawan
author_facet Wu, Hao
Ariza-Casabona, Alejandro
Twardowski, Bartłomiej
Wijaya, Tri Kurniawan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_07222
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MM-GEF: Multi-modal representation meet collaborative filtering
Wu, Hao
Ariza-Casabona, Alejandro
Twardowski, Bartłomiej
Wijaya, Tri Kurniawan
Information Retrieval
Artificial Intelligence
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.
title MM-GEF: Multi-modal representation meet collaborative filtering
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2308.07222