IMETA-GNN: Meta Learning-Based Cold Start Optimization for Recommendation System

Recommendation systems are becoming essential components of contemporary online goods and services, and they significantly affect customer satisfaction. Recommendation systems are designed to empower customers in their decision-making process by providing personalized recommendations. Meta-learning...

Full description

Saved in:
Bibliographic Details
Main Authors: Nida Siddique, Amna Zafar, Beenish Ayesha Akram, Muhammad Waseem, Sajid Iqbal, Ahmad A. Al-Yahya, Muhammad Nabeel Asghar, Abdullah Abdulrrehman Alaulamie
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10977006/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850232520330706944
author Nida Siddique
Amna Zafar
Beenish Ayesha Akram
Muhammad Waseem
Sajid Iqbal
Ahmad A. Al-Yahya
Muhammad Nabeel Asghar
Abdullah Abdulrrehman Alaulamie
author_facet Nida Siddique
Amna Zafar
Beenish Ayesha Akram
Muhammad Waseem
Sajid Iqbal
Ahmad A. Al-Yahya
Muhammad Nabeel Asghar
Abdullah Abdulrrehman Alaulamie
author_sort Nida Siddique
collection DOAJ
description Recommendation systems are becoming essential components of contemporary online goods and services, and they significantly affect customer satisfaction. Recommendation systems are designed to empower customers in their decision-making process by providing personalized recommendations. Meta-learning has proven to be effective in addressing user cold-start problems in recommendation systems. Many meta-learning-based recommendation systems designed for the cold-start problem are gradient-based. The existing frameworks require optimization techniques to maximize the potential of hyper networks, enabling them to adapt and generate compatible parameters for efficient learning as meta-learners. However, these frameworks often lack contextual knowledge from users to provide suitable initial guidelines in the recommendation network for new users. We propose a meta-learning-based framework that improves cold-start recommendation accuracy by incorporating user behavior and preferences. Evaluations on MovieLens 100K and DBook datasets show our IMETA-GNN model outperforms state-of-the-art baselines, achieving accuracies of 82% and 75%, respectively. Performance evaluation demonstrates that our proposed method outperforms several state-of-the-art metalearning recommendation systems in addressing the user cold-start conundrum.
format Article
id doaj-art-5c3f9bc7c6094161abe7efb7516efef4
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-5c3f9bc7c6094161abe7efb7516efef42025-08-20T02:03:08ZengIEEEIEEE Access2169-35362025-01-0113939649397610.1109/ACCESS.2025.356445410977006IMETA-GNN: Meta Learning-Based Cold Start Optimization for Recommendation SystemNida Siddique0Amna Zafar1https://orcid.org/0000-0002-7270-7238Beenish Ayesha Akram2https://orcid.org/0000-0002-5348-9132Muhammad Waseem3https://orcid.org/0000-0001-9605-2531Sajid Iqbal4https://orcid.org/0000-0002-8464-2275Ahmad A. Al-Yahya5Muhammad Nabeel Asghar6https://orcid.org/0000-0002-9487-4344Abdullah Abdulrrehman Alaulamie7Department of Computer Science, University of Engineering and Technology, Lahore, PakistanDepartment of Computer Science, University of Engineering and Technology, Lahore, PakistanDepartment of Computer Science, University of Engineering and Technology, Lahore, PakistanDepartment of Computer Science, University of Engineering and Technology, Lahore, PakistanDepartment of Information Systems, College of Computer Science and Information Technology, King Faisal University, Alahsa, Saudi ArabiaDepartment of Information Systems, College of Computer Science and Information Technology, King Faisal University, Alahsa, Saudi ArabiaDepartment of Information Systems, College of Computer Science and Information Technology, King Faisal University, Alahsa, Saudi ArabiaDepartment of Information Systems, College of Computer Science and Information Technology, King Faisal University, Alahsa, Saudi ArabiaRecommendation systems are becoming essential components of contemporary online goods and services, and they significantly affect customer satisfaction. Recommendation systems are designed to empower customers in their decision-making process by providing personalized recommendations. Meta-learning has proven to be effective in addressing user cold-start problems in recommendation systems. Many meta-learning-based recommendation systems designed for the cold-start problem are gradient-based. The existing frameworks require optimization techniques to maximize the potential of hyper networks, enabling them to adapt and generate compatible parameters for efficient learning as meta-learners. However, these frameworks often lack contextual knowledge from users to provide suitable initial guidelines in the recommendation network for new users. We propose a meta-learning-based framework that improves cold-start recommendation accuracy by incorporating user behavior and preferences. Evaluations on MovieLens 100K and DBook datasets show our IMETA-GNN model outperforms state-of-the-art baselines, achieving accuracies of 82% and 75%, respectively. Performance evaluation demonstrates that our proposed method outperforms several state-of-the-art metalearning recommendation systems in addressing the user cold-start conundrum.https://ieeexplore.ieee.org/document/10977006/Cold start problemmeta-learningrecommendation systemGNNoptimization
spellingShingle Nida Siddique
Amna Zafar
Beenish Ayesha Akram
Muhammad Waseem
Sajid Iqbal
Ahmad A. Al-Yahya
Muhammad Nabeel Asghar
Abdullah Abdulrrehman Alaulamie
IMETA-GNN: Meta Learning-Based Cold Start Optimization for Recommendation System
IEEE Access
Cold start problem
meta-learning
recommendation system
GNN
optimization
title IMETA-GNN: Meta Learning-Based Cold Start Optimization for Recommendation System
title_full IMETA-GNN: Meta Learning-Based Cold Start Optimization for Recommendation System
title_fullStr IMETA-GNN: Meta Learning-Based Cold Start Optimization for Recommendation System
title_full_unstemmed IMETA-GNN: Meta Learning-Based Cold Start Optimization for Recommendation System
title_short IMETA-GNN: Meta Learning-Based Cold Start Optimization for Recommendation System
title_sort imeta gnn meta learning based cold start optimization for recommendation system
topic Cold start problem
meta-learning
recommendation system
GNN
optimization
url https://ieeexplore.ieee.org/document/10977006/
work_keys_str_mv AT nidasiddique imetagnnmetalearningbasedcoldstartoptimizationforrecommendationsystem
AT amnazafar imetagnnmetalearningbasedcoldstartoptimizationforrecommendationsystem
AT beenishayeshaakram imetagnnmetalearningbasedcoldstartoptimizationforrecommendationsystem
AT muhammadwaseem imetagnnmetalearningbasedcoldstartoptimizationforrecommendationsystem
AT sajidiqbal imetagnnmetalearningbasedcoldstartoptimizationforrecommendationsystem
AT ahmadaalyahya imetagnnmetalearningbasedcoldstartoptimizationforrecommendationsystem
AT muhammadnabeelasghar imetagnnmetalearningbasedcoldstartoptimizationforrecommendationsystem
AT abdullahabdulrrehmanalaulamie imetagnnmetalearningbasedcoldstartoptimizationforrecommendationsystem