用检索增强生成异步时间序列，提升长期预测稳定性与多样性
ReDiTT: Retrieval Augmented Conditional Diffusion Transformers for Asynchronous Time Series
- 在潜在空间检索相似序列作为条件，通过交叉注意力引导生成
- 在7个真实数据集上实现最先进性能，长期预测更稳定且样本更丰富
- 适合需要高可靠性时序预测的工业场景或金融风险建模
我们提出一种基于扩散模型的异步时间序列预测方法，目标是预测下一个事件的时间间隔和事件类型。为应对未来事件的固有不确定性，我们引入ReDiTT——一种在潜在空间中运行的检索增强条件扩散变压器。ReDiTT在训练和推理阶段均从记忆库中检索结构相似的潜在序列，并通过交叉注意力将其作为参考条件。这种基于检索的条件化使模型能够关注相关的时间动态，并为生成提供全局结构指导。结果表明，ReDiTT显著提升了长周期预测的稳定性并改善了样本多样性。在七个真实世界数据集上的实验验证了其在下一次事件预测和长周期预测任务中的最先进性能。代码已公开于https://github.com/BorealisAI/ReDiTT。
原文摘要 · Abstract (English)
We present a diffusion based model for asynchronous time series prediction, where the goal is to predict the next inter event time and event type. To address the inherent uncertainty of future events, we introduce ReDiTT, a retrieval augmented conditional diffusion transformer that operates in latent space. ReDiTT retrieves structurally similar latent sequences from a memory bank during both training and inference and incorporates them as reference conditions through cross attention. This retrieval based conditioning allows the model to attend to relevant temporal dynamics and provides global structural guidance for generation. As a result, ReDiTT stabilizes long horizon forecasting and improves sample diversity. Experiments on seven real world datasets demonstrate state of the art performance on next event prediction and long horizon forecasting. Our code is available at https://github.com/BorealisAI/ReDiTT.
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。