解决数据稀缺下的时间序列生成难题，提升小样本场景下模型泛化能力。
Towards a Unified Generative Model for Scarce Time Series with Domain Experts
- 融合扩散变换器与专家混合机制，增强跨领域适应性。
- 在低数据条件下显著优于现有方法，实现更高质量的时间序列生成。
- 适合需要少样本生成的工业、金融等实际场景使用。
生成真实时间序列在现实应用中具有广泛前景。尽管已有进展，但多数方法依赖充足训练数据，难以适用于数据稀缺场景。本文提出 TimeMoDE 框架，结合扩散变换器与专家混合（Mixture-of-Experts），在数据稀缺下实现领域自适应与扩散阶段感知。该模型在大规模多领域数据集上预训练，学习通用时序表征与领域特定信息，促进微调时的泛化能力。我们引入领域提示（Domain Prompts）以条件化专家分配，应对噪声标记不可区分的问题，缓解跨数据集关系捕捉不足。同时，融入扩散时间步信号，使专家具备对时间序列退化变化的感知，实现针对不同去噪阶段的自适应校准。大量实验表明，TimeMoDE 在多种低数据设置下均优于现有方法，开创了先进的时间序列少样本生成新范式。
原文摘要 · Abstract (English)
Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios. Despite recent progress, most existing methods are trained under the assumption of abundant training data, which substantially limits their effectiveness in data-scarce settings. In this paper, we propose TimeMoDE, a novel framework that integrates Diffusion Transformers with Mixture-of-Experts to exploit both domain adaptability and diffusion-stage awareness for time series generation under data scarcity. It is pre-trained on a large-scale collection of multi-domain datasets to extract domain-agnostic temporal representations and domain-specific information benefiting generalization during fine-tuning. We propose Domain Prompts to condition expert assignment for indistinguishable noised tokens, mitigating the limitations of capturing inter-dataset relationships. Moreover, we incorporate diffusion timestep signals to equip the experts with awareness of time series degradation variations, facilitating adaptive calibrate to stage-dependent denoising requirements. Extensive experiments demonstrate that TimeMoDE outperforms existing methods under diverse low-data settings. It establishes an innovative paradigm for advanced time series few-shot generation.
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。