用两步法生成不规则时间序列，效果更好且更快。
A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking
- 先用Transformer补全数据，再用视觉扩散模型生成。
- 相比之前方法，判别分数提升70%，计算成本降低85%。
- 适合医疗、金融等领域需要高质量时间序列的场景。
生成真实的时间序列数据在医疗、金融和科学领域至关重要。然而，不规则采样和缺失值带来了巨大挑战。尽管已有方法处理这些不规则性，但往往效果不佳且计算开销大。最近基于扩散模型的ImagenTime通过将时间序列转换为图像表示，在规则序列生成上展现出强大、快速且可扩展的能力。然而，直接对不规则序列使用简单掩码会引入“不自然”的邻域，零值填充破坏学习过程。为此，我们提出一种新型两步框架：首先，时间序列Transformer完成不规则序列，构建自然邻域；其次，基于视觉的扩散模型结合掩码机制，降低对补全值的依赖。该方法融合了补全与掩码的优势，实现稳健高效的高质量时间序列生成。实验表明，本方法在判别分数上相对提升70%，计算成本降低85%。代码已开源：https://github.com/azencot-group/ImagenI2R。
原文摘要 · Abstract (English)
Generating realistic time series data is critical for applications in healthcare, finance, and science. However, irregular sampling and missing values present significant challenges. While prior methods address these irregularities, they often yield suboptimal results and incur high computational costs. Recent advances in regular time series generation, such as the diffusion-based ImagenTime model, demonstrate strong, fast, and scalable generative capabilities by transforming time series into image representations, making them a promising solution. However, extending ImagenTime to irregular sequences using simple masking introduces "unnatural" neighborhoods, where missing values replaced by zeros disrupt the learning process. To overcome this, we propose a novel two-step framework: first, a Time Series Transformer completes irregular sequences, creating natural neighborhoods; second, a vision-based diffusion model with masking minimizes dependence on the completed values. This approach leverages the strengths of both completion and masking, enabling robust and efficient generation of realistic time series. Our method achieves state-of-the-art performance, achieving a relative improvement in discriminative score by $70\%$ and in computational cost by $85\%$. Code is at https://github.com/azencot-group/ImagenI2R.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。