arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.28867cs.LGcs.AI
收藏

PrismFlow: 时间序列生成中流匹配的残差动力学

PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation

Zhejiang University, China(浙江大学,中国);Nanyang Technological University, Singapore(南洋理工大学,新加坡);I2R, Agency for Science, Technology and Research (A*STAR), Singapore(科技研究局(A*STAR)新加坡研究所,新加坡)

Junru Zhang, Lang Feng, Jinbo Wang, Xu Guo, Yucheng Wang, Han Yu, Min Wu, Yabo Dong, Duanqing Xu

AI总结:

提出PrismFlow方法,通过Koopman启发的动力学专家和置信度感知的胜者全得目标,在流匹配中学习残差修正,以解决标准流匹配中全局向量场估计器导致的频谱失真和模式覆盖不足问题,在时间序列生成中取得最优性能。

摘要:

生成高质量时间序列数据具有挑战性,因为现实世界的信号通常表现出多模态模式和多尺度动力学,包括振荡和高频变化。流匹配(FM)为扩散模型提供了一种高效的替代方案,但实际实现通常依赖于单个有限容量的全局向量场估计器。在这种异质的时间分布中,不同的状态可能通过邻近的流状态,同时需要不相容的条件速度。使用标准$\ell_2$速度匹配目标训练的单一估计器可能学习到局部传输场的过度平滑近似。这种估计器级别的平滑会减弱分支特定的动力学,导致频谱失真和较差的模式覆盖。为了解决这个问题,我们提出了PrismFlow,一种新的具有Koopman启发动力学专家的FM方法。每个专家在一个潜在空间中学习残差修正,其中局部非线性时间演化可以通过线性变换近似。我们进一步提出了一种置信度感知的胜者全得(WTA)目标,该目标仅更新与每个样本最对齐的专家,同时屏蔽其他专家的梯度,鼓励模式特定专业化。在采样过程中,选定的专家向全局传输场添加残差动力学修正,在保持FM稳定性的同时恢复细粒度和高频时间结构。在各种基准测试中,PrismFlow有效缓解了标准FM中的频谱收缩,并实现了最先进的性能,Context-FID提升了15.6%,判别分数提升了38.6%,同时在低数据设置下保持鲁棒性,并有效用于预测和插补。

英文摘要:

Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an efficient alternative to diffusion models, but practical implementations typically rely on a single finite-capacity global vector-field estimator. In such heterogeneous temporal distributions, distinct regimes may pass through nearby flow states while requiring incompatible conditional velocities. A monolithic estimator trained with the standard $\ell_2$ velocity-matching objective may therefore learn an overly smoothed approximation of the local transport field. This estimator-level smoothing can attenuate branch-specific dynamics, leading to spectral distortion and poor mode coverage. To address this, we propose PrismFlow, a new FM method with Koopman-inspired dynamical experts. Each expert learns residual corrections in a latent space where local nonlinear temporal evolution can be approximated by linear transitions. We further propose a confidence-aware Winner-Take-All (WTA) objective that updates only the expert best aligned with each sample while masking gradients to the others, encouraging mode-specific specialization. During sampling, the selected expert adds a residual dynamical correction to the global transport field, preserving FM stability while recovering fine-grained and high-frequency temporal structures. Across various benchmarks, PrismFlow effectively mitigates the spectral contraction in standard FM and achieves state-of-the-art performance, with a 15.6% gain in Context-FID and a 38.6% improvement in Discriminative Score, while remaining robust in low-data settings and effective for forecasting and imputation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑