Paper: arXiv 2412.04034

Authors: Yunhua Pei, Jin Zheng, John Cartlidge

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.

Complexity vs Empirical Score

  • Math Complexity: 7.0/10
  • Empirical Rigor: 8.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper involves advanced graph neural networks, contrastive learning, and Fourier transforms, requiring dense mathematical notation (high math). It includes extensive experiments on two real market datasets (NASDAQ, NYSE), ablation studies, and offers public code/data, demonstrating strong empirical validation.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Predict Stock Trends by Integrating<br>Dynamic Temporal & Static Relational Data"] --> B["Data Input<br>NYSE & NASDAQ Stock Market Datasets"]
  
  B --> C["Proposed Framework: DGRCL<br>Dynamic Graph Representation with Contrastive Learning"]
  
  C --> D["Dynamic Component<br>Embedding Enhancement EE Module<br>Captures Temporal Evolution"]
  C --> E["Static Component<br>Contrastive Constrained Training CCT Module<br>Enforces Stock Relation Constraints"]
  
  D & E --> F["Computational Process<br>Contrastive Learning Integration<br>Refines Dynamic & Static Representations"]
  
  F --> G["Outcomes<br>Superior Prediction Accuracy vs SOTA Baselines"]
  F --> H["Outcomes<br>Robust Framework for Dynamic Graph Analysis"]
  F --> I["Outcomes<br>Public Code & Data Availability"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes the Dynamic Graph Representation with Contrastive Learning (DGRCL) framework, which integrates dynamic temporal graph learning and static relational graph learning via an Embedding Enhancement (EE) module and a Contrastive Constrained Training (CCT) module.

Source sentence
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 Co

Assumes 5

  • Dynamic edges are constructed adaptively following Zipf’s law. model
    Source sentence
    In embedding enhancement, we adaptively construct dynamic edges that follow Zipf’s law.
  • The trade‑off parameter λ balances prediction loss and contrastive loss. model
    Source sentence
    The final form of the loss function is shown below, where λ is a trade‑off parameter.
  • Sector‑industry relationships adequately capture static relational constraints among stocks. data
    Source sentence
    Recognizing that stocks within the same industry tend to be similarly affected by industry‑wide prospects, we gather data on the sector‑industry relationships among stocks.
  • Training, validation and test splits are 0.65, 0.1, and 0.25 of the total trading days respectively. data
    Source sentence
    We follow the setup of (Pareja et al., 2020) and divide the two datasets into training, validation, and testing sets in the proportions of 0.65, 0.1, and 0.25, respectively.
Show 1 more
  • OHLCV daily values are sufficient features for stock prediction. data
    Source sentence
    OHLCV are daily values for each stock.

Data

No dataset named in the text.

Costs

Not applicable The paper reports no trading or execution result.

Finds 3

  • DGRCL achieves the highest classification accuracy on the NASDAQ dataset (53.06%) and NYSE dataset (54.07%), outperforming all baselines. performance
    Source sentence
    On the NYSE dataset, DGRCL similarly outperforms other methods, with an accuracy of 54.07%.
  • DGRCL attains the top F1 scores of 66.53% (NASDAQ) and 67.53% (NYSE), and strong MCC values of 9.32×10⁻³ and 27.51×10⁻³ respectively. predictive-accuracy
    Source sentence
    and a substantial MCC of 27.51, marking the highest recorded metrics across all models.
  • Training time is dominated by the CCT module, which accounts for around 90% of total runtime (≈414 s on NASDAQ, ≈506 s on NYSE). other
    Source sentence
    The full DGRCL model, which includes these enhancements, requires 414.05s on NASDAQ and 505.54s on NYSE. Notably, adding the CCT unit significantly increases the training time, accounting for around 90% of the total run-time.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 32 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (221)

  1. The patent holder’s dilemma: Buy, sell, or troll? (2007) — link
  2. Deciding equivalances among conjunctive aggregate queries (2007) — link
  3. Special issue: Digital Libraries (1996)
  4. Understanding Policy-Based Networking (2001)
  5. First-Order Dynamic Logic (1979) — link
  6. The title of book one (2007) — link
  7. The title of book two (2008) — link
  8. Achieving application requirements (1990) — link
and 213 more
  1. Statecarts in use: structured analysis and object-orientation (1998) — link
  2. The Art of Computer Programming, Vol. 1: Fundamental Algorithms (3rd. ed.) (1997)
  3. The Art of Computer Programming (1998)
  4. An experiment in bibliographic mark-up: Parsing metadata for XML export (2010) — link
  5. Catch me, if you can: Evading network signatures with web-based polymorphic worms (2007)
  6. Catch me, if you can: Evading network signatures with web-based polymorphic worms (2008)
  7. Catch me, if you can: Evading network signatures with web-based polymorphic worms (2009)
  8. Predicate Path expressions (1979) — link
  9. LOGICS of Programs: AXIOMATICS and DESCRIPTIVE POWER (1978)
  10. Optimal Motion Control of a Ground Vehicle (2003)
  11. Algorithms for Closest-Point Problems (Computational Geometry) (1985)
  12. Introduction to Bayesian Statistics (2001) — link
  13. CLIFFORD: a Maple 11 Package for Clifford Algebra Computations, version 11 (2007) — link
  14. Stats and Analysis (2006) — link
  15. A more perfect union (2008) — link
  16. The fountain of youth (2009)
  17. Solder man (2003) — link
  18. Interview with Bill Kinder: January 13, 2005 (2005) — link
  19. The Enabling of Digital Libraries (2008)
  20. (old) Finding minimum congestion spanning trees (2000) — link
  21. (new) Finding minimum congestion spanning trees (2000) — link
  22. (old) Distributed data source verification in wireless sensor networks (2009) — link
  23. (new) Distributed data source verification in wireless sensor networks (2009) — link
  24. Portalis: using competitive online interactions to support aid initiatives for the homeless (2008) — link
  25. Visual Basic 6: Design, Specification, and Objects with Other (1999)
  26. The Latex Web Companion: Integrating TEX, HTML, and XML (1999)
  27. Vertex Types in Book-Embeddings (1987)
  28. Vertex Types in Book-Embeddings (1987)
  29. CHI ‘08: CHI ‘08 extended abstracts on Human factors in computing systems (2008)
  30. Algorithms for Closest-Point Problems (Computational Geometry) (1985)
  31. IEEE TCSC Executive Committee (2004) — link
  32. Distributed systems (2nd Ed.) (1993)
  33. New Algorithms for Dependency-Directed Backtracking (Master’s thesis) (1986)
  34. New Algorithms for Dependency-Directed Backtracking (Master’s thesis) (1986)
  35. Seminumerical Algorithms (1981)
  36. E-commerce and cultural values (2001) — link
  37. Chapter 9 (2002) — link
  38. The implementation of electronic commerce in SMEs in Singapore (Incoll) (2003) — link
  39. E-commerce and cultural values - (InBook-num-in-chap) (2004) — link
  40. E-commerce and cultural values (Inbook-text-in-chap) (2005) — link
  41. E-commerce and cultural values (Inbook-num chap) (2006) — link
  42. A library-based synthesis methodology for reversible logic (2010)
  43. Synthesis of Reversible Circuit Using Cycle-Based Approach (2010)
  44. Algorithmic Enumeration of Ideal Classes for Quaternion Orders (2010) — link
  45. Chapter II: Notes on data structuring (1972) — link
  46. Transcript of question and answer session (1981) — link
  47. Go to statement considered harmful (1979) — link
  48. Three-dimensional virtual acoustic displays (1992) — link
  49. Managerial expert systems and organizational change: some critical research issues (1987) — link
  50. Simplified Structured COBOL with Microsoft/MicroFocus COBOL (1990)
  51. A multi-radio unification protocol for IEEE 802.11 wireless networks (2004)
  52. Wireless Sensor Networks: A Survey (2002)
  53. A Survey on Wireless Multimedia Sensor Networks (2007)
  54. SSCH : Slotted Seeded Channel Hopping for Capacity Improvement in IEEE 802.11 Ad-Hoc Wireless Networks (2004)
  55. XBOW Sensor Motes Specifications (2008)
  56. Overview of Sensor Networks (2004)
  57. CodeBlue : Sensor Networks for Medical Care (2008)
  58. Investigating Network Architectures for Body Sensor Networks (2007)
  59. Channel-Hopping Multiple Access (2000)
  60. Body Sensor Networks (2008)
  61. Mapping Powerlists onto Hypercubes (1994)
  62. Automatic Parallelization for Distributed-Memory Multiprocessing Systems (1989)
  63. User recovery and reversal in interactive systems (1984)
  64. Generalizing specifications for uniformly implemented loops (1985)
  65. Towards monolingual programming environments (1985)
  66. The \TeX book (1984)
  67. Distributed algorithms for finding centers and medians in networks (1984)
  68. \it \LaTeX : A Document Preparation System (1986)
  69. Program transformations in a denotational setting (1985)
  70. Seminumerical Algorithms (1981)
  71. A high-level approach to computer document formatting (1980)
  72. A multifrequency MAC specially designed for wireless sensor network applications (2010) — link
  73. Institutional members of the \TeX Users Group (2017) — link
  74. acmart— C lass for typesetting publications of ACM (2017) — link
  75. Reasoning About Naming Systems (1993) — link
  76. Babel, a Multilingual Style-Option System for Use with LaTeX’s Standard Document Styles (1991)
  77. A Methodology for Implementing Highly Concurrent Data Objects (1993) — link
  78. Publication quality tables in \LaTeX (2005)
  79. Using the amsthm Package (2015)
  80. R: A Language and Environment for Statistical Computing (2019) — link
  81. UMass Citation Field Extraction Dataset (2013) — link
  82. Citation concept analysis (CCA): a new form of citation analysis revealing the usefulness of concepts for other researchers illustrated by exemplary case studies including classic books by Thomas S. Kuhn and Karl R. Popper (2020)
  83. Maintaining Discrete Probability Distributions Optimally (1993)
  84. Efficient capital markets: A review of theory and empirical work (1970)
  85. Twitter mood predicts the stock market (2011)
  86. Forecasting closing price indices using neural networks (2006)
  87. Pricing stocks with yardsticks and sentiments (2011)
  88. A systematic review of fundamental and technical analysis of stock market predictions (2020)
  89. A LSTM -based method for stock returns prediction: A case study of C hina stock market (2015)
  90. The Limit Order Book Recreation Model (LOBRM): An Extended Analysis (2021)
  91. Constrained formulations and algorithms for stock-price predictions using recurrent FIR neural networks (2002)
  92. Domain adaptive multi-modality neural attention network for financial forecasting (2020)
  93. Hybrid deep sequential modeling for social text-driven stock prediction (2018)
  94. Stock movement prediction from tweets and historical prices (2018)
  95. Investment behaviors can tell what inside: Exploring stock intrinsic properties for stock trend prediction (2019)
  96. Classification and prediction of stock market index based on fuzzy metagraph (2015)
  97. Evaluating multiple classifiers for stock price direction prediction (2015)
  98. Individualized indicator for all: Stock-wise technical indicator optimization with stock embedding (2019)
  99. Stock market’s price movement prediction with LSTM neural networks (2017)
  100. HGNN: Hierarchical graph neural network for predicting the classification of price-limit-hitting stocks (2022)
  101. Deep direct reinforcement learning for financial signal representation and trading (2016)
  102. Tensor-based learning for predicting stock movements (2015)
  103. Deep learning for stock prediction using numerical and textual information (2016)
  104. Knowledge-driven stock trend prediction and explanation via temporal convolutional network (2019)
  105. Knowledge-driven event embedding for stock prediction (2016)
  106. Astock: A New Dataset and Automated Stock Trading based on Stock-specific News Analyzing Model (2022) — link
  107. Price prediction of share market using artificial neural network (ANN) (2011)
  108. Deep attentive learning for stock movement prediction from social media text and company correlations (2020)
  109. Time-aware graph relational attention network for stock recommendation (2020)
  110. Accurate multivariate stock movement prediction via data-axis transformer with multi-level contexts (2021)
  111. Fuzzy hypergraph network for recommending top-K profitable stocks (2022)
  112. Temporal-relational hypergraph tri-attention networks for stock trend prediction (2023)
  113. Stock selection via spatiotemporal hypergraph attention network: A learning to rank approach (2021)
  114. Temporal relational ranking for stock prediction (2019)
  115. A survey of the application of graph-based approaches in stock market analysis and prediction (2022)
  116. A comprehensive survey on graph neural networks (2020)
  117. Graph attention networks (2017)
  118. Semi-Supervised Classification with Graph Convolutional Networks (2017) — link
  119. Inductive representation learning on large graphs (2017)
  120. How Powerful are Graph Neural Networks? (2019) — link
  121. Learning to simulate complex physics with graph networks (2020)
  122. Applications of graph theory in chemistry (1985)
  123. Social networks (2013)
  124. Deep learning (2015)
  125. Graph-based stock recommendation by time-aware relational attention network (2021)
  126. Deep learning (2016)
  127. Backpropagation applied to handwritten zip code recognition (1989)
  128. Recurrent neural networks (2001)
  129. Generative adversarial networks: An overview (2018)
  130. Autoencoders (2020)
  131. Evolve GCN : Evolving graph convolutional networks for dynamic graphs (2020)
  132. Stock exchange merger and liquidity: The case of Euronext (2009)
  133. Random walks in stock market prices (1995)
  134. A causal feature selection algorithm for stock prediction modeling (2014)
  135. Exploiting social media for stock market prediction with factorization machine (2014)
  136. Integrating metaheuristics and artificial neural networks for improved stock price prediction (2016)
  137. Learning multiple stock trading patterns with temporal routing adaptor and optimal transport (2021)
  138. Deep learning with long short-term memory networks for financial market predictions (2018)
  139. Attention is all you need (2017)
  140. Adaptive stock trading strategies with deep reinforcement learning methods (2020)
  141. Graph-based stock correlation and prediction for high-frequency trading systems (2022)
  142. Can online emotions predict the stock market in China? (2016)
  143. Do Weibo Platform Experts Perform Better at Predicting Stock Market? (2021)
  144. Listening to chaotic whispers: A deep learning framework for news-oriented stock trend prediction (2018)
  145. Investor sentiment in the stock market (2007)
  146. Surveying stock market forecasting techniques–Part II: Soft computing methods (2009)
  147. Forecasting stock market short-term trends using a neuro-fuzzy based methodology (2009)
  148. The sharpe ratio (1998)
  149. Stock price prediction using machine learning and LSTM -based deep learning models (2021)
  150. Financial Portfolio Management Based on Shaped-Based Unsupervised Machine Learning: A Dynamic Time Warping Baycenter Averaging Approach to International Markets and Periods of Downside Event Risks (2022)
  151. A two-level reinforcement learning algorithm for ambiguous mean-variance portfolio selection problem (2021)
  152. Online portfolio selection with cardinality constraint and transaction costs based on contextual bandit (2021)
  153. Market manipulation: An adversarial learning framework for detection and evasion (2020)
  154. Physics-aware difference graph networks for sparsely-observed dynamics (2019)
  155. Visual interaction networks: Learning a physics simulator from video (2017)
  156. Learning the graphical structure of electronic health records with graph convolutional transformer (2020)
  157. Retrosynthesis prediction with conditional graph logic network (2019)
  158. Graph convolutional networks for text classification (2019)
  159. DeepRank-GNN : a graph neural network framework to learn patterns in protein–protein interfaces (2023)
  160. Spatio-temporal dynamic inference network for group activity recognition (2021)
  161. Graph contrastive learning automated (2021)
  162. Graph contrastive learning with adaptive augmentation (2021)
  163. Gnnexplainer: Generating explanations for graph neural networks (2019)
  164. AddGraph: Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN. (2019)
  165. Deep into hypersphere: Robust and unsupervised anomaly discovery in dynamic networks (2018)
  166. Modeling the stock relation with graph network for overnight stock movement prediction (2021)
  167. A novel graph convolutional feature based convolutional neural network for stock trend prediction (2021)
  168. Financial time series forecasting with multi-modality graph neural network (2022)
  169. HATS : A hierarchical graph attention network for stock movement prediction (2019) — link
  170. Fin GAT : Financial Graph Attention Networks for Recommending Top-K Profitable Stocks (2021)
  171. Adaptive long-short pattern transformer for stock investment selection (2022)
  172. EMD2FNN: A strategy combining empirical mode decomposition and factorization machine based neural network for stock market trend prediction (2019)
  173. CLVSA : A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets (2019) — link
  174. Exploring the attention mechanism in LSTM -based H ong K ong stock price movement prediction (2019)
  175. Multi-task recurrent neural networks and higher-order M arkov random fields for stock price movement prediction: Multi-task RNN and higher-order MRF s for stock price classification (2019)
  176. A study on novel filtering and relationship between input-features and target-vectors in a deep learning model for stock price prediction (2019)
  177. Stock movement prediction based on bi-typed hybrid-relational market knowledge graph via dual attention networks (2022)
  178. Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysis (2019)
  179. Forecasting the market with machine learning algorithms: an application of NMC-BERT-LSTM-DQN-X algorithm in quantitative trading (2022)
  180. Emergence of scaling in random networks (1999)
  181. Exploring the scale-free nature of stock markets: Hyperbolic graph learning for algorithmic trading (2021)
  182. Power laws, P areto distributions and Z ipf’s law (2005)
  183. Weighted dynamic time warping for time series classification (2011)
  184. Reversible instance normalization for accurate time-series forecasting against distribution shift (2021)
  185. Ada RNN : Adaptive learning and forecasting of time series (2021)
  186. What is the fast F ourier transform? (1967)
  187. Fourier analysis of time series: An introduction (2004)
  188. On the rationale of maximum-entropy methods (1982)
  189. Contrastive multi-view representation learning on graphs (2020)
  190. Networks (2018)
  191. Information transfer between stock market sectors: A comparison between the USA and China (2020)
  192. Dysat: Deep neural representation learning on dynamic graphs via self-attention networks (2020)
  193. Graph wavenet for deep spatial-temporal graph modeling (2019)
  194. Domain-adversarial training of neural networks (2016)
  195. Deep coral: Correlation alignment for deep domain adaptation (2016)
  196. Optimal kernel choice for large-scale two-sample tests (2012)
  197. Constructing equity portfolios from sec 13f data using feature extraction and machine learning (2020)
  198. Deeplob: Deep convolutional neural networks for limit order books (2019)
  199. Benchmark dataset for mid-price forecasting of limit order book data with machine learning methods (2018)
  200. Challenges and opportunities in deep reinforcement learning with graph neural networks: A comprehensive review of algorithms and applications (2023)
  201. Multivariate time series forecasting with dynamic graph neural ODE s (2022)
  202. When do contrastive learning signals help spatio-temporal graph forecasting? (2022)
  203. DGDNN : Decoupled graph diffusion neural network for stock movement prediction (2024)
  204. A comparison of volatility and bid–ask spread for NASDAQ and NYSE after decimalization (2011)
  205. An Empirical Examination of VIX Market Fluctuations (2022)
  206. Graph self-supervised learning: A survey (2022)
  207. Deep graph infomax. (2019)
  208. Graph contrastive learning with augmentations (2020)
  209. Iterative graph self-distillation (2023)
  210. Deep graph infomax. (2019)
  211. Efficient integration of multi-order dynamics and internal dynamics in stock movement prediction (2023)
  212. HIST : A graph-based framework for stock trend forecasting via mining concept-oriented shared information (2021) — link
  213. Multi-Relational Graph Diffusion Neural Network with Parallel Retention for Stock Trends Classification — → 2401.05430

1 of 221 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.