Efficient Visual-Aware Fashion Recommendation Using Compressed Node Features and Graph-Based Learning

In fashion e-commerce, predicting item compatibility using visual features remains a significant challenge. Current recommendation systems often struggle to incorporate high-dimensional visual data into graph-based learning models effectively. This limitation presents a substantial opportunity to en...

Full description

Saved in:
Bibliographic Details
Main Authors: Umar Subhan Malhi, Junfeng Zhou, Abdur Rasool, Shahbaz Siddeeq
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Machine Learning and Knowledge Extraction
Subjects:
Online Access:https://www.mdpi.com/2504-4990/6/3/104
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850260399798091776
author Umar Subhan Malhi
Junfeng Zhou
Abdur Rasool
Shahbaz Siddeeq
author_facet Umar Subhan Malhi
Junfeng Zhou
Abdur Rasool
Shahbaz Siddeeq
author_sort Umar Subhan Malhi
collection DOAJ
description In fashion e-commerce, predicting item compatibility using visual features remains a significant challenge. Current recommendation systems often struggle to incorporate high-dimensional visual data into graph-based learning models effectively. This limitation presents a substantial opportunity to enhance the precision and effectiveness of fashion recommendations. In this paper, we present the Visual-aware Graph Convolutional Network (VAGCN). This novel framework helps improve how visual features can be incorporated into graph-based learning systems for fashion item compatibility predictions. The VAGCN framework employs a deep-stacked autoencoder to convert the input image’s high-dimensional raw CNN visual features into more manageable low-dimensional representations. In addition to improving feature representation, the GCN can also reason more intelligently about predictions, which would not be possible without this compression. The GCN encoder processes nodes in the graph to capture structural and feature correlation. Following the GCN encoder, the refined embeddings are input to a multi-layer perceptron (MLP) to calculate compatibility scores. The approach extends to using neighborhood information only during the testing phase to help with training efficiency and generalizability in practical scenarios, a key characteristic of our model. By leveraging its ability to capture latent visual features and neighborhood-based learning, VAGCN thoroughly investigates item compatibility across various categories. This method significantly improves predictive accuracy, consistently outperforming existing benchmarks. These contributions tackle significant scalability and computational efficiency challenges, showcasing the potential transformation of recommendation systems through enhanced feature representation, paving the way for further innovations in the fashion domain.
format Article
id doaj-art-ebbfe94ab6304116a578a54aa9cd6b6a
institution OA Journals
issn 2504-4990
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Machine Learning and Knowledge Extraction
spelling doaj-art-ebbfe94ab6304116a578a54aa9cd6b6a2025-08-20T01:55:38ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902024-09-01632111212910.3390/make6030104Efficient Visual-Aware Fashion Recommendation Using Compressed Node Features and Graph-Based LearningUmar Subhan Malhi0Junfeng Zhou1Abdur Rasool2Shahbaz Siddeeq3School of Computer Science and Technology, Donghua University, Songjiang, Shanghai 200051, ChinaSchool of Computer Science and Technology, Donghua University, Songjiang, Shanghai 200051, ChinaDepartment of Information and Computer Sciences, University of Hawaii at Manoa, Honolulu, HI 96822, USAFaculty of Information Technology and Communication Sciences, Tampere University, 33100 Tampere, FinlandIn fashion e-commerce, predicting item compatibility using visual features remains a significant challenge. Current recommendation systems often struggle to incorporate high-dimensional visual data into graph-based learning models effectively. This limitation presents a substantial opportunity to enhance the precision and effectiveness of fashion recommendations. In this paper, we present the Visual-aware Graph Convolutional Network (VAGCN). This novel framework helps improve how visual features can be incorporated into graph-based learning systems for fashion item compatibility predictions. The VAGCN framework employs a deep-stacked autoencoder to convert the input image’s high-dimensional raw CNN visual features into more manageable low-dimensional representations. In addition to improving feature representation, the GCN can also reason more intelligently about predictions, which would not be possible without this compression. The GCN encoder processes nodes in the graph to capture structural and feature correlation. Following the GCN encoder, the refined embeddings are input to a multi-layer perceptron (MLP) to calculate compatibility scores. The approach extends to using neighborhood information only during the testing phase to help with training efficiency and generalizability in practical scenarios, a key characteristic of our model. By leveraging its ability to capture latent visual features and neighborhood-based learning, VAGCN thoroughly investigates item compatibility across various categories. This method significantly improves predictive accuracy, consistently outperforming existing benchmarks. These contributions tackle significant scalability and computational efficiency challenges, showcasing the potential transformation of recommendation systems through enhanced feature representation, paving the way for further innovations in the fashion domain.https://www.mdpi.com/2504-4990/6/3/104fashion recommendation systemsrepresentation learninggraph convolutional networks
spellingShingle Umar Subhan Malhi
Junfeng Zhou
Abdur Rasool
Shahbaz Siddeeq
Efficient Visual-Aware Fashion Recommendation Using Compressed Node Features and Graph-Based Learning
Machine Learning and Knowledge Extraction
fashion recommendation systems
representation learning
graph convolutional networks
title Efficient Visual-Aware Fashion Recommendation Using Compressed Node Features and Graph-Based Learning
title_full Efficient Visual-Aware Fashion Recommendation Using Compressed Node Features and Graph-Based Learning
title_fullStr Efficient Visual-Aware Fashion Recommendation Using Compressed Node Features and Graph-Based Learning
title_full_unstemmed Efficient Visual-Aware Fashion Recommendation Using Compressed Node Features and Graph-Based Learning
title_short Efficient Visual-Aware Fashion Recommendation Using Compressed Node Features and Graph-Based Learning
title_sort efficient visual aware fashion recommendation using compressed node features and graph based learning
topic fashion recommendation systems
representation learning
graph convolutional networks
url https://www.mdpi.com/2504-4990/6/3/104
work_keys_str_mv AT umarsubhanmalhi efficientvisualawarefashionrecommendationusingcompressednodefeaturesandgraphbasedlearning
AT junfengzhou efficientvisualawarefashionrecommendationusingcompressednodefeaturesandgraphbasedlearning
AT abdurrasool efficientvisualawarefashionrecommendationusingcompressednodefeaturesandgraphbasedlearning
AT shahbazsiddeeq efficientvisualawarefashionrecommendationusingcompressednodefeaturesandgraphbasedlearning