QFCQT：用于 volatile 时间序列预测的混沌门控 Quantformer 框架
QFCQT: A Chaotically Gated Quantformer Framework for Volatile Time-Series Forecasting
浏览论文内容
中文总结 AI 辅助
该研究针对 volatile 时间序列预测难题，提出 QFCQT 框架，采用量化编码器、Lee 振荡器激活模块与混沌门控融合机制，在多基准上优于现有强基线方法。
中文摘要 AI 辅助
预测非平稳时间序列仍然存在困难，原因在于其存在长程依赖、局部 volatility 突发、结构变化以及非线性振荡行为。尽管基于 Transformer 的预测器在建模长期时间依赖方面效果显著，但其前馈块通常依赖平滑的静态激活函数，对突发的状态变化不够敏感。受量化 Transformer 设计和基于振荡器的非线性激活函数的启发，我们提出了 QFCQT，即 Quantum-Fractal-inspired Chaotically Gated Quantformer（量子分形启发的混沌门控 Quantformer）的缩写，用于在复杂 volatile 动态下进行稳健预测。此处的“量子分形启发”指的是基于软振荡器叠加和多尺度非线性响应的计算类比，而非正式的量子力学或分形理论推导。QFCQT 包含三个主要组件：（1）Quantformer 风格的数值编码器，通过线性嵌入直接处理多变量输入；（2）可学习的 Lee 振荡器激活模块，将标量预激活映射为动态振荡响应，并通过 Max-over-Time 池化对其进行汇总；（3）平滑混沌门控融合机制，自适应平衡传统平滑激活与对混沌敏感的响应。此外，QFCQT 未使用单个固定振荡器，而是采用八个参数化 Lee 振荡器族的软叠加，以自适应捕捉不同状态下的不同非线性响应模式。在 ETTh1、ETTh2 和 A 股指数基准上的实验表明，QFCQT 始终优于 Informer、LogTrans、LSTMa、HAT 和 COTN 等强基线方法。
英文摘要
Forecasting non-stationary time series remains difficult due to long-range dependencies, local volatility bursts, structural shifts, and nonlinear oscillatory behaviors. Although Transformer-based forecasters are effective for modeling long-term temporal dependencies, their feed-forward blocks typically rely on smooth static activations that are insufficiently sensitive to abrupt regime changes. Motivated by quantitative Transformer designs and oscillator-based nonlinear activations, we propose QFCQT, short for Quantum-Fractal-inspired Chaotically Gated Quantformer, for robust forecasting under complex volatile dynamics. Here, "quantum-fractal-inspired" denotes a computational analogy based on soft oscillator superposition and multi-scale nonlinear responses, rather than a formal quantum-mechanical or fractal-theoretic derivation. QFCQT consists of three main components: (1) a Quantformer-style numerical encoder that directly processes multivariate inputs via linear embedding; (2) a learnable Lee-oscillator activation module that maps scalar pre-activations to dynamic oscillatory responses and summarizes them through Max-over-Time pooling; and (3) a smooth-chaotic gated fusion mechanism that adaptively balances conventional smooth activations and chaos-sensitive responses. Furthermore, instead of using a single fixed oscillator, QFCQT employs a soft superposition of eight parameterized Lee oscillator families to adaptively capture different nonlinear response patterns across regimes. Experiments on ETTh1, ETTh2, and A-share Stock Index benchmarks show that QFCQT consistently outperforms strong baselines, including Informer, LogTrans, LSTMa, HAT, and COTN.
