# FactorGCL: A Hypergraph-Based Factor Model with Temporal Residual Contrastive Learning for Stock Returns Prediction

arXiv: https://arxiv.org/abs/2502.05218 · HTML: https://mlsanity.com/paper/2502.05218/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 39 references that are in the map.
- First posted on arXiv 5 Feb 2025.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Hypergraph Neural Networks](https://mlsanity.com/paper/1809.09401/) (2018)
- [A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction](https://mlsanity.com/paper/1704.02971/) (2017)
- [Hypergraph Convolution and Hypergraph Attention](https://mlsanity.com/paper/1901.08150/) (2019)
- [Towards Unsupervised Deep Graph Structure Learning](https://mlsanity.com/paper/2201.06367/) (2022)
- [AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework](https://mlsanity.com/paper/2403.12582/) (2024)
- [HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information](https://mlsanity.com/paper/2110.13716/) (2021)
- [Astock: A New Dataset and Automated Stock Trading based on Stock-specific News Analyzing Model](https://mlsanity.com/paper/2206.06606/) (2022)

## Built on by (most cited first, 9 of 9)

- [MEME: Modeling the Evolutionary Modes of Financial Markets](https://mlsanity.com/paper/2602.11918/) (2026)
- [Vector-Quantized Discrete Latent Factors Meet Financial Priors: Dynamic Cross-Sectional Stock Ranking Prediction for Portfolio Construction](https://mlsanity.com/paper/2605.13407/) (2026)
- [Signature-Informed Transformer for Asset Allocation](https://mlsanity.com/paper/2510.03129/) (2025)
- [MaGNet: A Mamba Dual-Hypergraph Network for Stock Prediction via Temporal-Causal and Global Relational Learning](https://mlsanity.com/paper/2511.00085/) (2025)
- [GAPNet: Plug-in Jointly Learning Task-Specific Graph for Dynamic Stock Relation](https://mlsanity.com/paper/2602.00888/) (2026)
- [ACT: Anti-Crosstalk Learning for Cross-Sectional Stock Ranking via Temporal Disentanglement and Structural Purification](https://mlsanity.com/paper/2604.20204/) (2026)
- [AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining](https://mlsanity.com/paper/2609.29014/) (2026)
- [STOCK-JEPA: Prior-Anchored Latent Revision Representation Learning in Equity Markets](https://mlsanity.com/paper/2610.07006/) (2026)
- [DPAL: A Test-Time Adaptation Loss for Financial Time Series Forecasting](https://mlsanity.com/paper/2610.14376/) (2026)

## Abstract (arXiv)

As a fundamental method in economics and finance, the factor model has been extensively utilized in quantitative investment. In recent years, there has been a paradigm shift from traditional linear models with expert-designed factors to more flexible nonlinear machine learning-based models with data-driven factors, aiming to enhance the effectiveness of these factor models. However, due to the low signal-to-noise ratio in market data, mining effective factors in data-driven models remains challenging. In this work, we propose a hypergraph-based factor model with temporal residual contrastive learning (FactorGCL) that employs a hypergraph structure to better capture high-order nonlinear relationships among stock returns and factors. To mine hidden factors that supplement human-designed prior factors for predicting stock returns, we design a cascading residual hypergraph architecture, in which the hidden factors are extracted from the residual information after removing the influence of prior factors. Additionally, we propose a temporal residual contrastive learning method to guide the extraction of effective and comprehensive hidden factors by contrasting stock-specific residual information over different time periods. Our extensive experiments on real stock market data demonstrate that FactorGCL not only outperforms existing state-of-the-art methods but also mines effective hidden factors for predicting stock returns.