# NGAT: A Node-level Graph Attention Network for Long-term Stock Prediction

arXiv: https://arxiv.org/abs/2507.02018 · HTML: https://mlsanity.com/paper/2507.02018/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 31 references that are in the map.
- First posted on arXiv 2 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [Temporal Relational Ranking for Stock Prediction](https://mlsanity.com/paper/1809.09441/) (2018)
- [Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction](https://mlsanity.com/paper/2305.08740/) (2023)
- [Evaluating Financial Relational Graphs: Interpretation Before Prediction](https://mlsanity.com/paper/2410.07216/) (2024)

## Built on by (most cited first, 5 of 5)

- [Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis](https://mlsanity.com/paper/2511.06437/) (2025)
- [GAPNet: Plug-in Jointly Learning Task-Specific Graph for Dynamic Stock Relation](https://mlsanity.com/paper/2602.00888/) (2026)
- [Relational Probing: LM-to-Graph Adaptation for Financial Prediction](https://mlsanity.com/paper/2604.10212/) (2026)
- [ACT: Anti-Crosstalk Learning for Cross-Sectional Stock Ranking via Temporal Disentanglement and Structural Purification](https://mlsanity.com/paper/2604.20204/) (2026)
- [Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios](https://mlsanity.com/paper/2609.35086/) (2026)

## Abstract (arXiv)

Graph representation learning methods have been widely adopted in financial applications to enhance company representations by leveraging inter-firm relationships. However, current approaches face three key challenges: (1) The advantages of relational information are obscured by limitations in downstream task designs; (2) Existing graph models specifically designed for stock prediction often suffer from excessive complexity and poor generalization; (3) Experience-based construction of corporate relationship graphs lacks effective comparison of different graph structures. To address these limitations, we propose a long-term stock prediction task and develop a Node-level Graph Attention Network (NGAT) specifically tailored for corporate relationship graphs. Furthermore, we experimentally demonstrate the limitations of existing graph comparison methods based on model downstream task performance. Experimental results across two datasets consistently demonstrate the effectiveness of our proposed task and model. The project is publicly available on GitHub to encourage reproducibility and future research.