Analysis of Developments and Challenges in Dealing with Recommender System Cold-Start Issue

Yue Zhong

2025

Abstract

The cold-start problem, caused by a lack of historical interaction data, remains a significant challenge for recommender systems. This study explores three strategies to address this issue: knowledge graphs, meta-learning, and large language models. The meta-learning method, Dual enhanced Meta-learning with Adaptive Task Scheduler (DMATS), improves embedding accuracy and task adaptation through autonomous learning. The knowledge graph method, Knowledge-Enhanced Graph Learning (KEGL), enhances recommendation quality using collaborative embeddings and knowledge-enhanced attention. The large language model method, Automated Dis-entangled Sequential recommendation (AutoDisenSeq-LLM), optimizes recommendations by leveraging text understanding. These methods were tested on datasets like MovieLens, Amazon, and Yelp. The meta-learning method demonstrated strong generalization, the knowledge graph method tackled data sparsity, and the language model method showed potential but needed further improvement. Challenges include high computational costs, lack of standardized evaluation metrics, and dataset issues. Future research should focus on novel techniques, datasets, and metrics.

Paper Citation

in Harvard Style

Zhong Y. (2025). Analysis of Developments and Challenges in Dealing with Recommender System Cold-Start Issue. In Proceedings of the 2nd International Conference on Public Relations and Media Communication - Volume 1: PRMC; ISBN 978-989-758-778-8, SciTePress, pages 289-295. DOI: 10.5220/0013990300004916

in Bibtex Style

@conference{prmc25,
author={Yue Zhong},
title={Analysis of Developments and Challenges in Dealing with Recommender System Cold-Start Issue},
booktitle={Proceedings of the 2nd International Conference on Public Relations and Media Communication - Volume 1: PRMC},
year={2025},
pages={289-295},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013990300004916},
isbn={978-989-758-778-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Public Relations and Media Communication - Volume 1: PRMC
TI - Analysis of Developments and Challenges in Dealing with Recommender System Cold-Start Issue
SN - 978-989-758-778-8
AU - Zhong Y.
PY - 2025
SP - 289
EP - 295
DO - 10.5220/0013990300004916
PB - SciTePress