Dynamic Graph Representation with Contrastive Learning for Financial Market Prediction: Integrating Temporal Evolution and Static Relations

Yunhua Pei, Jin Zheng, John Cartlidge

2025

Abstract

Temporal Graph Learning (TGL) is crucial for capturing the evolving nature of stock markets. Traditional methods often ignore the interplay between dynamic temporal changes and static relational structures between stocks. To address this issue, we propose the Dynamic Graph Representation with Contrastive Learning (DGRCL) framework, which integrates dynamic and static graph relations to improve the accuracy of stock trend prediction. Our framework introduces two key components: the Embedding Enhancement (EE) module and the Contrastive Constrained Training (CCT) module. The EE module focuses on dynamically capturing the temporal evolution of stock data, while the CCT module enforces static constraints based on stock relations, refined within contrastive learning. This dual-relation approach allows for a more comprehensive understanding of stock market dynamics. Our experiments on two major U.S. stock market datasets, NASDAQ and NYSE, demonstrate that DGRCL significantly outperforms state-of-the-art TGL baselines. Ablation studies indicate the importance of both modules. Overall, DGRCL not only enhances prediction ability but also provides a robust framework for integrating temporal and relational data in dynamic graphs. Code and data are available for public access.

Paper Citation

in Harvard Style

Pei Y., Zheng J. and Cartlidge J. (2025). Dynamic Graph Representation with Contrastive Learning for Financial Market Prediction: Integrating Temporal Evolution and Static Relations. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 298-309. DOI: 10.5220/0013154700003890

in Bibtex Style

@conference{icaart25,
author={Yunhua Pei and Jin Zheng and John Cartlidge},
title={Dynamic Graph Representation with Contrastive Learning for Financial Market Prediction: Integrating Temporal Evolution and Static Relations},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={298-309},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013154700003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Dynamic Graph Representation with Contrastive Learning for Financial Market Prediction: Integrating Temporal Evolution and Static Relations
SN - 978-989-758-737-5
AU - Pei Y.
AU - Zheng J.
AU - Cartlidge J.
PY - 2025
SP - 298
EP - 309
DO - 10.5220/0013154700003890
PB - SciTePress