IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2509.25055.html
   My bibliography  Save this paper

AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration

Author

Listed:
  • Binqi Chen
  • Hongjun Ding
  • Ning Shen
  • Jinsheng Huang
  • Taian Guo
  • Luchen Liu
  • Ming Zhang

Abstract

The automated mining of predictive signals, or alphas, is a central challenge in quantitative finance. While Reinforcement Learning (RL) has emerged as a promising paradigm for generating formulaic alphas, existing frameworks are fundamentally hampered by a triad of interconnected issues. First, they suffer from reward sparsity, where meaningful feedback is only available upon the completion of a full formula, leading to inefficient and unstable exploration. Second, they rely on semantically inadequate sequential representations of mathematical expressions, failing to capture the structure that determine an alpha's behavior. Third, the standard RL objective of maximizing expected returns inherently drives policies towards a single optimal mode, directly contradicting the practical need for a diverse portfolio of non-correlated alphas. To overcome these challenges, we introduce AlphaSAGE (Structure-Aware Alpha Mining via Generative Flow Networks for Robust Exploration), a novel framework is built upon three cornerstone innovations: (1) a structure-aware encoder based on Relational Graph Convolutional Network (RGCN); (2) a new framework with Generative Flow Networks (GFlowNets); and (3) a dense, multi-faceted reward structure. Empirical results demonstrate that AlphaSAGE outperforms existing baselines in mining a more diverse, novel, and highly predictive portfolio of alphas, thereby proposing a new paradigm for automated alpha mining. Our code is available at https://github.com/BerkinChen/AlphaSAGE.

Suggested Citation

  • Binqi Chen & Hongjun Ding & Ning Shen & Jinsheng Huang & Taian Guo & Luchen Liu & Ming Zhang, 2025. "AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration," Papers 2509.25055, arXiv.org, revised Sep 2025.
  • Handle: RePEc:arx:papers:2509.25055
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2509.25055
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Tianping Zhang & Yuanqi Li & Yifei Jin & Jian Li, 2020. "AutoAlpha: an Efficient Hierarchical Evolutionary Algorithm for Mining Alpha Factors in Quantitative Investment," Papers 2002.08245, arXiv.org, revised Apr 2020.
    2. Xiao Yang & Weiqing Liu & Dong Zhou & Jiang Bian & Tie-Yan Liu, 2020. "Qlib: An AI-oriented Quantitative Investment Platform," Papers 2009.11189, arXiv.org.
    3. Junjie Zhao & Chengxi Zhang & Chenkai Wang & Peng Yang, 2025. "Learning from Expert Factors: Trajectory-level Reward Shaping for Formulaic Alpha Mining," Papers 2507.20263, arXiv.org.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Haochen Luo & Yuan Zhang & Chen Liu, 2025. "EFS: Evolutionary Factor Searching for Sparse Portfolio Optimization Using Large Language Models," Papers 2507.17211, arXiv.org.
    2. Hongjun Ding & Binqi Chen & Jinsheng Huang & Taian Guo & Zhengyang Mao & Guoyi Shao & Lutong Zou & Luchen Liu & Ming Zhang, 2025. "AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining," Papers 2508.13174, arXiv.org.
    3. Shuo Yu & Hongyan Xue & Xiang Ao & Feiyang Pan & Jia He & Dandan Tu & Qing He, 2023. "Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning," Papers 2306.12964, arXiv.org.
    4. Feng Xu & Yan Yin & Xinyu Zhang & Tianyuan Liu & Shengyi Jiang & Zongzhang Zhang, 2024. "$\text{Alpha}^2$: Discovering Logical Formulaic Alphas using Deep Reinforcement Learning," Papers 2406.16505, arXiv.org, revised Jun 2024.
    5. Quechen Yang, 2024. "Blending Ensemble for Classification with Genetic-algorithm generated Alpha factors and Sentiments (GAS)," Papers 2411.03035, arXiv.org.
    6. Shuo Sun & Rundong Wang & Bo An, 2021. "Reinforcement Learning for Quantitative Trading," Papers 2109.13851, arXiv.org.
    7. Tao Ren & Ruihan Zhou & Jinyang Jiang & Jiafeng Liang & Qinghao Wang & Yijie Peng, 2024. "RiskMiner: Discovering Formulaic Alphas via Risk Seeking Monte Carlo Tree Search," Papers 2402.07080, arXiv.org, revised Feb 2024.
    8. Weizhe Ren & Yichen Qin & Yang Li, 2024. "Alpha Mining and Enhancing via Warm Start Genetic Programming for Quantitative Investment," Papers 2412.00896, arXiv.org.
    9. Lifan Zhao & Shuming Kong & Yanyan Shen, 2023. "DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting," Papers 2306.09862, arXiv.org, revised Apr 2024.
    10. Bruno Gav{s}perov & Marko {DJ}urasevi'c & Domagoj Jakobovic, 2024. "Finding Near-Optimal Portfolios With Quality-Diversity," Papers 2402.16118, arXiv.org.
    11. Wentao Xu & Weiqing Liu & Lewen Wang & Yingce Xia & Jiang Bian & Jian Yin & Tie-Yan Liu, 2021. "HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information," Papers 2110.13716, arXiv.org, revised Jan 2022.
    12. Yonggai Zhuang & Haoran Chen & Kequan Wang & Teng Fei, 2024. "GRU-PFG: Extract Inter-Stock Correlation from Stock Factors with Graph Neural Network," Papers 2411.18997, arXiv.org.
    13. Hang Yuan & Saizhuo Wang & Jian Guo, 2024. "Alpha-GPT 2.0: Human-in-the-Loop AI for Quantitative Investment," Papers 2402.09746, arXiv.org.
    14. Wentao Zhang & Yilei Zhao & Shuo Sun & Jie Ying & Yonggang Xie & Zitao Song & Xinrun Wang & Bo An, 2023. "Reinforcement Learning with Maskable Stock Representation for Portfolio Management in Customizable Stock Pools," Papers 2311.10801, arXiv.org, revised Feb 2024.
    15. Chujun He & Zhonghao Huang & Xiangguo Li & Ye Luo & Kewei Ma & Yuxuan Xiong & Xiaowei Zhang & Mingyang Zhao, 2025. "Hierarchical AI Multi-Agent Fundamental Investing: Evidence from China's A-Share Market," Papers 2510.21147, arXiv.org.
    16. Lili Wang & Chenghan Huang & Chongyang Gao & Weicheng Ma & Soroush Vosoughi, 2023. "Joint Latent Topic Discovery and Expectation Modeling for Financial Markets," Papers 2307.08649, arXiv.org.
    17. Yuan Gao & Haokun Chen & Xiang Wang & Zhicai Wang & Xue Wang & Jinyang Gao & Bolin Ding, 2024. "DiffsFormer: A Diffusion Transformer on Stock Factor Augmentation," Papers 2402.06656, arXiv.org.
    18. Jonghun Kwak & Jungyu Ahn & Jinho Lee & Sungwoo Park, 2022. "Shai-am: A Machine Learning Platform for Investment Strategies," Papers 2207.00436, arXiv.org.
    19. Saizhuo Wang & Hang Yuan & Leon Zhou & Lionel M. Ni & Heung-Yeung Shum & Jian Guo, 2023. "Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investment," Papers 2308.00016, arXiv.org, revised Sep 2025.
    20. Saizhuo Wang & Hao Kong & Jiadong Guo & Fengrui Hua & Yiyan Qi & Wanyun Zhou & Jiahao Zheng & Xinyu Wang & Lionel M. Ni & Jian Guo, 2025. "QuantBench: Benchmarking AI Methods for Quantitative Investment," Papers 2504.18600, arXiv.org.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2509.25055. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.