要预测股票涨跌？这篇论文搞了个自适应 Transformer，把95个金融指标分成11组，根据市场风向调整注意力，还省了15%的算力。
论文提出 Adaptive Financial Transformer (AFT) 模型，针对非平稳金融市场的股票收益预测。该模型包含市场体制编码器、自适应门网络和自适应金融上下文模块，基于 95 个金融特征（分为 11 个语义类别）动态偏置自注意力。与传统 Transformer 不同，AFT 根据潜在市场体制调整注意力，并通过复合目标同时优化预测误差、方向准确率和非重叠夏普比率。实验表明，AFT 在保持竞争性预测性能的同时，将模型复杂度降低 15.2%，参数效率得到提升。
Adaptive Financial Transformer with Regime-Gated Attention for Stock Return Prediction
Adaptive Financial Transformer (AFT) is proposed for stock return prediction under non-stationary financial markets. The model incorporates a Market Regime Encoder, an Adaptive Gate Network, and an Adaptive Financial Context module to dynamically bias self-attention based on semantic relationships between financial indicators. Unlike conventional Transformer architectures that treat all input features uniformly, the proposed approach groups 95 engineered financial features into 11 semantic categories and adapts attention according to latent market regimes. The study also identifies and corrects sequence alignment and backtesting issues that can inflate reported trading performance, and introduces a financially-aware composite objective that jointly optimizes prediction error, directional accuracy, and non-overlapping Sharpe ratio. Extensive experiments compare the proposed architecture against classical machine learning models, recurrent neural networks, and Transformer baselines using chronological evaluation, five random seeds, ablation studies, hyperparameter optimization, explainability analysis, and multi-stock validation. Results demonstrate competitive predictive performance while reducing model complexity by 15.2% and improving parameter efficiency through feature selection, providing an interpretable Transformer architecture for financial time-series forecasting.