Vol. 1 No. 1 (2026), Articles
Vol. 1 No. 1 (2026)

HeMoG: Heterogeneous Multi-Modal Graph Learning with Hierarchical Contrastive Loss for Stock Movement Prediction

Articles
Published 2026-05-10
  • Grace Mitchell
Grace Mitchell

Keywords

Stock Prediction
Heterogeneous Graph Neural Network

Abstract

Stock movement prediction remains a central challenge in financial machine learning due to the inherent noise, non-stationarity, and multi-source heterogeneity of market data. While recent approaches leveraging graph neural networks (GNNs) have achieved promising results by modeling relational structures among financial assets, most existing methods treat stocks as homogeneous nodes and rely on a single data modality. In this paper, we propose HeMoG (Heterogeneous Multi-Modal Graph Learning), a novel framework that constructs a heterogeneous stock graph incorporating price correlations, sectoral hierarchies, and macroeconomic factor linkages, and fuses these with multi-modal signals (numerical time series, textual news, and social media sentiment) through a cross-attention fusion mechanism. To address the challenge of learning discriminative stock representations under noisy labels, we introduce a Hierarchical Contrastive Loss (HCL) that operates at three levels: node-level stock embedding, sector-level prototype, and market-level global distribution. Extensive experiments conducted on three benchmark datasets (S&P 500, NASDAQ-100, and CSI-300) demonstrate that HeMoG outperforms ten competitive baseline models, including state-of-the-art approaches such as S3G (ICASSP 2026), achieving an average improvement of 4.7% in directional accuracy and 8.3% in Matthews Correlation Coefficient (MCC) across all datasets. Ablation studies confirm the significant contributions of both the heterogeneous graph structure and the hierarchical contrastive loss to model performance.

References

1. Araci, D. (2019). FinBERT: Financial Sentiment Analysis with Pre-trained Language Models. *Proceedings of the 1st Workshop on Financial Technology and Natural Language Processing*, pages 38-44.

2. Ba, J.L., Kiros, J.R., and Hinton, G.E. (2016). Layer Normalization. *arXiv preprint arXiv:1607.06450*.

3. Bai, S., Kolter, J.Z., and Koltun, V. (2018). An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. *arXiv preprint arXiv:1803.01271*.

4. Chen, J., Dong, H., Wang, X., Wu, F., and Xie, X. (2021). Graph Neural Networks for Cryptocurrency Price Prediction. *IEEE Transactions on Knowledge and Data Engineering*, 35(8): 8246-8258.

5. Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. *International Conference on Machine Learning (ICML)*, pages 1597-1607.

6. Chen, W., and Wei, D. (2022). FinGraph: Graph Contrastive Learning for Financial Risk Management. *Proceedings of the 28th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining*, pages 1894-1903.

7. Chen, Y., Lu, Y., and Wang, B. (2020). Stock Movement Prediction with Sector Information using Graph Convolutional Networks. *IEEE Transactions on Neural Networks and Learning Systems*, 31(12): 5419-5429.

8. Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. *Conference on Empirical Methods in Natural Language Processing (EMNLP)*, pages 1724-1734.

9. Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. *Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)*, pages 4171-4186.

10. Fama, E.F. (1965). The Behavior of Stock-Market Prices. *Journal of Business*, 38(1): 34-105.

11. Fey, M., and Lenssen, J.E. (2019). Fast Graph Representation Learning with PyTorch Geometric. *International Conference on Learning Representations (ICLR) Workshop*.

12. Fischer, T., and Krauss, C. (2018). Deep Learning with Long Short-Term Memory Networks for Financial Market Predictions. *European Journal of Operational Research*, 270(2): 654-669.

13. He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep Residual Learning for Image Recognition. *IEEE Conference on Computer Vision and Pattern Recognition (CVPR)*, pages 770-778.

14. Hendrycks, D., and Gimpel, K. (2016). Gaussian Error Linear Units (GELU). *arXiv preprint arXiv:1606.08415*.

15. Hochreiter, S., and Schmidhuber, J. (1997). Long Short-Term Memory. *Neural Computation*, 9(8): 1735-1780.

16. Kim, S., Lee, H., and Park, J. (2022). Heterogeneous Graph Neural Networks for Stock Prediction with Macroeconomic Indicators. *Proceedings of the AAAI Conference on Artificial Intelligence*, pages 12876-12884.

17. Kipf, E.N., and Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. *International Conference on Learning Representations (ICLR)*.

18. Le-Khac, N.A., O'Connor, N.E., and Jones, G.J.F. (2022). Market-Regime Invariant Stock Representation Learning via Contrastive Learning. *IEEE Transactions on Big Data*, 8(4): 1024-1036.

19. Li, T., Zhou, K., and Sercu, T. (2023). Stockformer: A Unified Approach for Multi-Horizon Stock Prediction. *arXiv preprint arXiv:2301.10536*.

20. Li, Y., Yu, R., Shahabi, C., and Liu, Y. (2018). Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. *International Conference on Learning Representations (ICLR)*.

21. Lim, B., Arık, S.Ö., Loeff, N., and Pfister, T. (2021). Temporal Fusion Transformers for Interpretable Multi-Horizon Time Series Forecasting. *International Journal of Forecasting*, 37(4): 1748-1764.

22. Liu, X., Li, T., Zhang, R., and Chen, G. (2021). StockNet++: Temporal Contrastive Learning for Stock Representation. *Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI)*, pages 4524-4530.

23. Liu, Y., Zhao, Q., and Wang, S. (2018). Credit Risk Assessment with Graph Neural Networks. *Proceedings of the 27th ACM International Conference on Information and Knowledge Management*, pages 2180-2188.

24. Loshchilov, I., and Hutter, F. (2019). Decoupled Weight Decay Regularization. *International Conference on Learning Representations (ICLR)*.

25. Lu, Y., Hu, K., and Zhang, L. (2026). S3G: Stock State Space Graph for Enhanced Stock Trend Prediction. *ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing*, pages 4081-4085. IEEE.

26. Malkiel, B.G. (2003). The Efficient Market Hypothesis and Its Critics. *Journal of Economic Perspectives*, 17(1): 59-82.

27. Oord, A.V.D., Li, Y., and Vinyals, O. (2018). Representation Learning with Contrastive Predictive Coding. *arXiv preprint arXiv:1807.03748*.

28. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., ... and Chintala, S. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. *Advances in Neural Information Processing Systems (NeurIPS)*, pages 8026-8037.

29. Qin, Y., Song, D., Chen, H., Cheng, W., Jiang, G., and Cottrell, G. (2017). A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction. *International Joint Conference on Artificial Intelligence (IJCAI)*, pages 2627-2633.

30. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. *Journal of Machine Learning Research*, 15(56): 1929-1958.

31. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., ... and Polosukhin, I. (2017). Attention Is All You Need. *Advances in Neural Information Processing Systems (NeurIPS)*, pages 5998-6008.

32. Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2018). Graph Attention Networks. *International Conference on Learning Representations (ICLR)*.

33. Wang, Q., Meng, F., and Liu, J. (2019). Knowledge-Graph Enhanced Stock Prediction. *Proceedings of the 28th ACM International Conference on Information and Knowledge Management*, pages 2181-2189.

34. Wu, J., Cui, Z., Du, J., and Wang, Y. (2023). FinGPT: Large Language Models for Financial Forecasting. *arXiv preprint arXiv:2308.10835*.

35. Wu, L., Cui, P., Pei, J., Zhao, J., and Song, L. (2022). Graph Neural Networks in Recommender Systems: A Survey. *ACM Computing Surveys*, 55(5): 1-37.

36. Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., and Philip, S.Y. (2020). A Comprehensive Survey on Graph Neural Networks. *IEEE Transactions on Neural Networks and Learning Systems*, 32(1): 4-24.

37. Xu, D., Ruan, C., Korpeoglu, E., Kumar, S., and Achan, K. (2021). Inductive Representation Learning on Temporal Graphs. *International Conference on Learning Representations (ICLR)*.

38. Yang, C., Kuo, P.H., and Su, C. (2023). Leveraging Pre-trained Language Models for Financial Sentiment Analysis. *Journal of Finance and Data Science*, 9(2): 134-152.

39. Yang, H., Liu, X.Y., Zhong, S., and Walid, A. (2019). Deep Reinforcement Learning for Portfolio Management. *Proceedings of the 27th ACM International Conference on Information and Knowledge Management*, pages 2069-2072.

40. Zhang, J., Zhang, R., Sun, R., Zhang, Y., and Wang, W. (2020). Robust Temporal convolutional Network for Stock Price Prediction. *IEEE Access*, 8: 189593-189602.

41. Zhang, K., Zulkernine, F., and Haque, A. (2017).Insider Threat Detection Using Deep Learning. *IEEE International Conference on Big Data (Big Data)*, pages 4613-4620.

42. Zhang, X., Li, Y., and Wang, S. (2017). Stock Trading with Graph Convolutional Networks. *Proceedings of the 26th International Conference on World Wide Web Companion*, pages 1363-1372.

43. Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, C., Xiong, H., and Zhang, W. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. *AAAI Conference on Artificial Intelligence*, pages 11106-11113.