arXiv：cs.LG· Lin Jiang, Rongchao Xu, Guang Wang·· 10 小时前
CrossTF：跨视图时频扩散实现极端事件感知的时间序列生成
Cross-View Time-Frequency Diffusion for Extreme-Aware Time-Series Generation
AI 导读
研究提出 CrossTF，利用时间视图与频率视图去噪器之间的差异（跨视图不对称性）实现极端事件感知的时间序列生成。该方法在训练并冻结两个去噪器后，只需在后期跨视图窗口内用基于极值理论的目标学习逐步融合参数。在 7 个真实数据集上与 11 个基线对比，极端保真度提升 26.1%，整体性能提升 7.4%。
正文
Abstract:Generating realistic time-series requires faithfully reproducing rare but high-impact extreme events. Existing approaches often rely on specialized representations or extreme-focused training objectives, which may restrict the diversity of captured extremes or compromise overall distributional fidelity. We propose Cross-View Time-Frequency Diffusion (CrossTF), a framework that exploits discrepancies between time- and frequency-view denoisers for extreme-aware time-series generation. Our key empirical finding is extreme-sensitive cross-view asymmetry: moving along the direction connecting the two views' clean-sample estimates substantially changes extreme fidelity while having limited effects on overall generation quality. We further identify a late-stage cross-view window in which this discrepancy stabilizes and cross-view adjustments have a particularly strong effect on extreme fidelity. These findings motivate a staged optimization strategy in CrossTF: after training and freezing both denoisers, it only needs to learn step-specific fusion parameters within this window using an Extreme Value Theory-based objective under an energy-distance constraint. This formulation supports interpolation between and extrapolation beyond the view-specific estimates while limiting degradation in overall generation quality. Extensive experiments on seven real-world datasets against 11 baselines show that CrossTF improves extreme fidelity by 26.1% and overall performance by 7.4% relative to the strongest baselines. These results highlight cross-view discrepancy as an effective basis for low-dimensional optimization in extreme-aware time-series generation.
| Comments: | 42 pages, 17 figures. Under Submission |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17407 [cs.LG] |
| (or arXiv:2610.17407v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17407 arXiv-issued DOI via DataCite |
Submission history
From: Lin Jiang [view email]
[v1]
Mon, 12 Oct 2026 21:13:37 UTC (34,392 KB)
[v2]
Wed, 14 Oct 2026 17:05:28 UTC (34,392 KB)
来源：arXiv：cs.LG · arxiv.org