此次不同：从可观测性视角看时间序列基础模型

This Time is Different: An Observability Perspective on Time Series Foundation Models

May 20, 2025

作者: Ben Cohen, Emaad Khwaja, Youssef Doubli, Salahidine Lemaachi, Chris Lettieri, Charles Masson, Hugo Miccinilli, Elise Ramé, Qiqi Ren, Afshin Rostamizadeh, Jean Ogier du Terrail, Anna-Monica Toon, Kan Wang, Stephan Xie, David Asker, Ameet Talwalkar, Othmane Abou-Amal

cs.AI

摘要

我们推出Toto，一个拥有1.51亿参数的时间序列预测基础模型。Toto采用现代仅解码器架构，并结合了针对多元可观测性时间序列数据特有挑战设计的架构创新。Toto的预训练语料库由可观测性数据、开放数据集和合成数据混合而成，其规模是领先时间序列基础模型的4至10倍。此外，我们引入了BOOM，一个包含2,807条真实世界时间序列、总计3.5亿观测点的大规模基准测试集。对于Toto和BOOM，我们仅从Datadog自身的遥测数据和内部可观测性指标中获取可观测性数据。广泛的评估表明，Toto在BOOM及现有通用时间序列预测基准测试上均达到了最先进的性能。Toto的模型权重、推理代码和评估脚本，以及BOOM的数据和评估代码，均以Apache 2.0许可证开源提供，访问地址为https://huggingface.co/Datadog/Toto-Open-Base-1.0和https://github.com/DataDog/toto。

English

We introduce Toto, a time series forecasting foundation model with 151 million parameters. Toto uses a modern decoder-only architecture coupled with architectural innovations designed to account for specific challenges found in multivariate observability time series data. Toto's pre-training corpus is a mixture of observability data, open datasets, and synthetic data, and is 4-10times larger than those of leading time series foundation models. Additionally, we introduce BOOM, a large-scale benchmark consisting of 350 million observations across 2,807 real-world time series. For both Toto and BOOM, we source observability data exclusively from Datadog's own telemetry and internal observability metrics. Extensive evaluations demonstrate that Toto achieves state-of-the-art performance on both BOOM and on established general purpose time series forecasting benchmarks. Toto's model weights, inference code, and evaluation scripts, as well as BOOM's data and evaluation code, are all available as open source under the Apache 2.0 License available at https://huggingface.co/Datadog/Toto-Open-Base-1.0 and https://github.com/DataDog/toto.