# STN-TGAT: Top-K Portfolio Construction via Prior-Guided Graph Attention with Learnable Soft-Threshold Sparsification

arXiv: https://arxiv.org/abs/2607.19385 · HTML: https://mlsanity.com/paper/2607.19385/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 36 references that are in the map.
- First posted on arXiv 1 Jul 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information](https://mlsanity.com/paper/2110.13716/) (2021)
- [DGDNN: Decoupled Graph Diffusion Neural Network for Stock Movement Prediction](https://mlsanity.com/paper/2401.01846/) (2024)
- [GCNET: graph-based prediction of stock price movement using graph convolutional network](https://mlsanity.com/paper/2203.11091/) (2022)
- [Hop-Hop Relation-aware Graph Neural Networks](https://mlsanity.com/paper/2012.11147/) (2020)
- [Forecasting Financial Market Structure from Network Features using Machine Learning](https://mlsanity.com/paper/2110.11751/) (2021)
- [Dynamic Deep Convolutional Candlestick Learner](https://mlsanity.com/paper/2201.08669/) (2022)

## Abstract (arXiv)

This paper tackles the problem of stock ranking and portfolio construction under realistic investment settings by jointly modeling temporal dynamics and cross-sectional dependencies. We propose the Soft-Threshold NMI-prior Transformer Graph Attention Network (STN-TGAT), which integrates a temporal Transformer with a Graph Attention Network to capture long-horizon sequential patterns and dynamic inter-stock relationships. An NMI-based prior graph combined with a soft-threshold sparsification mechanism enhances structural robustness by mitigating noisy correlations while preserving informative connections. The portfolio formation process incorporates practical considerations, including Top-5 selection within the Top-50 S&P 500 constituents, explicit weight allocation, and transaction cost adjustment, thereby aligning the evaluation with real-world trading conditions. Empirical results on real-world data demonstrate that STN-TGAT consistently outperforms benchmark models from predictive accuracy and investment profitability measured by portfolio returns. These findings suggest that combining decision-aligned training with adaptive relational modeling provides a coherent and practically effective framework for data-driven portfolio construction.