Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model

• URL: http://arxiv.org/abs/2506.11029v1
• Date: Tue, 20 May 2025 14:31:06 GMT
• Title: Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model
• Authors: Xue Wang, Tian Zhou, Jinyang Gao, Bolin Ding, Jingren Zhou,
• Abstract summary: This framework achieves state-of-the-art performance for our designed foundation model, YingLong.<n>YingLong is a non-causal, bidirectional attention encoder-only transformer trained through masked token recovery.<n>We release four foundation models ranging from 6M to 300M parameters, demonstrating superior results in zero-shot tasks.
• Score: 55.25659103706409
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We present a joint forecasting framework for time series prediction that contrasts with traditional direct or recursive methods. This framework achieves state-of-the-art performance for our designed foundation model, YingLong, and reveals a novel scaling effect: longer outputs significantly enhance model accuracy due to delayed chain-of-thought reasoning in our non-causal approach. YingLong is a non-causal, bidirectional attention encoder-only transformer trained through masked token recovery, aligning more effectively with language understanding tasks than with generation tasks. Additionally, we boost performance by tackling output variance with a multi-input ensemble. We release four foundation models ranging from 6M to 300M parameters, demonstrating superior results in zero-shot tasks on the ETT and Weather datasets. YingLong achieves more than 60% best performance. To ensure generalizability, we assessed the models using the GIFT-Eval benchmark, which comprises 23 time series datasets across 7 domains. Yinglong significantly outperformed the best time-series foundation models, end-to-end trained models by 14% and 44% in rank respectively.The pretrained 300M model is available at https://huggingface.co/qcw1314/YingLong_300m

Related papers

• A Mamba Foundation Model for Time Series Forecasting [13.593170999506889]
  We introduce TSMamba, a linear-complexity foundation model for time series forecasting built on the Mamba architecture. The model captures temporal dependencies through both forward and backward Mamba encoders, achieving high prediction accuracy. It also achieves competitive or superior full-shot performance compared to task-specific prediction models.
  arXiv  Detail & Related papers  (2024-11-05T09:34:05Z)
• Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts [25.503695417712997]
  Time-MoE is a scalable and unified architecture designed to pre-train larger, more capable forecasting foundation models.<n>Time-MoE enhances computational efficiency by activating only a subset of networks for each prediction.<n>For the first time, we scaled a time series foundation model up to 2.4 billion parameters, achieving significantly improved forecasting precision.
  arXiv  Detail & Related papers  (2024-09-24T12:42:18Z)
• No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance [68.18779562801762]
  multimodal models require exponentially more data to achieve linear improvements in downstream "zero-shot" performance. Our study reveals an exponential need for training data which implies that the key to "zero-shot" generalization capabilities under large-scale training paradigms remains to be found.
  arXiv  Detail & Related papers  (2024-04-04T17:58:02Z)
• Chronos: Learning the Language of Time Series [79.38691251254173]
  Chronos is a framework for pretrained probabilistic time series models. We show that Chronos models can leverage time series data from diverse domains to improve zero-shot accuracy on unseen forecasting tasks.
  arXiv  Detail & Related papers  (2024-03-12T16:53:54Z)
• Unified Training of Universal Time Series Forecasting Transformers [104.56318980466742]
  We present a Masked-based Universal Time Series Forecasting Transformer (Moirai) Moirai is trained on our newly introduced Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine domains. Moirai achieves competitive or superior performance as a zero-shot forecaster when compared to full-shot models.
  arXiv  Detail & Related papers  (2024-02-04T20:00:45Z)
• Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting [54.04430089029033]
  We present Lag-Llama, a general-purpose foundation model for time series forecasting based on a decoder-only transformer architecture. Lag-Llama is pretrained on a large corpus of diverse time series data from several domains, and demonstrates strong zero-shot generalization capabilities. When fine-tuned on relatively small fractions of such previously unseen datasets, Lag-Llama achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-10-12T12:29:32Z)
• Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domain [54.67888148566323]
  We introduce three large-scale time series forecasting datasets from the cloud operations domain. We show it is a strong zero-shot baseline and benefits from further scaling, both in model and dataset size. Accompanying these datasets and results is a suite of comprehensive benchmark results comparing classical and deep learning baselines to our pre-trained method.
  arXiv  Detail & Related papers  (2023-10-08T08:09:51Z)
• Unified Long-Term Time-Series Forecasting Benchmark [0.6526824510982802]
  We present a comprehensive dataset designed explicitly for long-term time-series forecasting. We incorporate a collection of datasets obtained from diverse, dynamic systems and real-life records. To determine the most effective model in diverse scenarios, we conduct an extensive benchmarking analysis using classical and state-of-the-art models. Our findings reveal intriguing performance comparisons among these models, highlighting the dataset-dependent nature of model effectiveness.
  arXiv  Detail & Related papers  (2023-09-27T18:59:00Z)
• Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection [40.21502451136054]
  This work presents DGHL, a new family of generative models for time series anomaly detection. A top-down Convolution Network maps a novel hierarchical latent space to time series windows, exploiting temporal dynamics to encode information efficiently. Our method outperformed current state-of-the-art models on four popular benchmark datasets.
  arXiv  Detail & Related papers  (2022-02-15T17:19:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.