Research map / Reinforcement learning / Visual and representation RL
AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration
Binqi Chen, Hongjun Ding, Ning Shen, Taian Guo, Jinsheng Huang, Luchen Liu, Ming Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add early stopping alone to plain GFlowNet (ablation) | GFlowNet alpha miner · CSI300 | Sharpe ratio: 0.72 -> -0.11 | Hurt |
| replace LSTM sequence encoder with GNN (RGCN) encoder (ablation) | GFlowNet + ES · CSI300 | IC: 0.046 -> 0.070 | Improved |
| replace LSTM with GNN encoder (ablation) | GFlowNet + ES · CSI300 | Sharpe ratio: -0.11 -> 1.25 | Improved |
| add structure-aware reward (ablation) | GFlowNet + ES + GNN · CSI300 | Sharpe ratio: 1.25 -> 1.14; MDD -19.4% -> -17.6% | Mixed |
| add novelty reward (ablation) | GFlowNet + ES + GNN + SA · CSI300 | Sharpe ratio: 1.14 -> 1.53 | Improved |
| add entropy regularizer (ablation) | AlphaSAGE · CSI300 | Sharpe ratio: 1.53 -> 1.71 | Improved |
| add entropy regularizer (ablation) | AlphaSAGE · CSI300 | RICIR: 0.614 -> 0.583 | Hurt |
| use AlphaSAGE instead of best baselines | alpha mining · CSI500 | ICIR: 0.396 -> 0.379 | No clear effect |
| increase novelty reward weight beyond moderate levels (ablation) | AlphaSAGE · CSI300 | correlation and portfolio metrics | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- AlphaQCM — AlphaQCM: Alpha Discovery in Finance with Distributional Reinforcement Learning (ICML 2025) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- AlphaQCM: Alpha Discovery in Finance with Distributional Reinforcement Learning (ICML 2025 · similarity 0.90)
- AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning (NeurIPS 2026 · similarity 0.89)
- AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors (AAAI 2025 · similarity 0.89)
- AlphaPROBE: Alpha Mining via principled retriveval and on-graph biased evolution (NeurIPS 2026 · similarity 0.89)
- ThetaEvolve: Test-time Learning on Open Problems (ICML 2026 · similarity 0.85)
- R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
