Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization on new TS coming from different datasets? This work provides positive evidence to this using a broad meta-learning framework which we show subsumes many existing meta-learning algorithms. Our theoretical analysis suggests that residual connections act as a meta-learning adaptation mechanism, generating a subset of task-specific parameters based on a given TS input, thus gradually expanding the expressive power of the architecture on-the-fly. The same mechanism is shown via linearization analysis to have the interpretation of a sequential update of the final linear layer. Our empirical results on a wide range of data emphasize the importance of the identified meta-learning mechanisms for successful zero-shot univariate forecasting, suggesting that it is viable to train a neural network on a source TS dataset and deploy it on a different target TS dataset without retraining, resulting in performance that is at least as good as that of state-of-practice univariate forecasting models.
University of Oxford（牛津大学）；Mind Foundry Ltd.（思维铸造有限公司）
Recurrent neural networks (RNNs) are state-of-the-art in several sequential learning tasks, but they often require considerable amounts of data to generalise well. For many time series forecasting (TSF) tasks, only a few dozens of observations may be available at training time, which restricts use of this class of models. We propose a novel RNN-based model that directly addresses this problem by learning a shared feature embedding over the space of many quantised time series. We show how this enables our RNN framework to accurately and reliably forecast unseen time series, even when there is l…
NTT Communication Science Laboratories（NTT通信科学实验室）；NTT Software Innovation Center（NTT软件创新中心）
Time-series forecasting is important for many applications. Forecasting models are usually trained using time-series data in a specific target task. However, sufficient data in the target task might be unavailable, which leads to performance degradation. In this paper, we propose a few-shot learning method that forecasts a future value of a time-series in a target task given a few time-series in the target task. Our model is trained using time-series data in multiple training tasks that are different from target tasks. Our model uses a few time-series to build a forecasting function based on a…
Learning complex time series forecasting models usually requires a large amount of data, as each model is trained from scratch for each task/data set. Leveraging learning experience with similar datasets is a well-established technique for classification problems called few-shot classification. However, existing approaches cannot be applied to time-series forecasting because i) multivariate time-series datasets have different channels and ii) forecasting is principally different from classification. In this paper we formalize the problem of few-shot forecasting of time-series with heterogeneou…
NXAI GmbH（NXAI公司）；ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz（ELLIS单位、LIT AI实验室、机器学习研究所）；Interdisciplinary Transformation University Austria（跨学科转型大学奥地利）
Recent research on time series foundation models has primarily focused on forecasting, leaving it unclear how generalizable their learned representations are. In this study, we examine whether frozen pre-trained forecasting models can provide effective representations for classification. To this end, we compare different representation extraction strategies and introduce two model-agnostic embedding augmentations. Our experiments show that the best forecasting models achieve classification accuracy that matches or even surpasses that of state-of-the-art models pre-trained specifically for clas…
Lancaster University（兰卡斯特大学）；Technical University of Ostrava（俄斯特拉发技术大学）；Sharif University of Technology（谢里夫理工大学）
One of the challenging questions in time series forecasting is how to find the best algorithm. In recent years, a recommender system scheme has been developed for time series analysis using a meta-learning approach. This system selects the best forecasting method with consideration of the time series characteristics. In this paper, we propose a novel approach to focusing on some of the unanswered questions resulting from the use of meta-learning in time series forecasting. Therefore, three main gaps in previous works are addressed including, analyzing various subsets of top forecasters as inpu…
New micro-grid design with renewable energy sources and battery storage systems can help improve greenhouse gas emissions and reduce the operational cost. To provide an effective short-/long-term forecasting of both energy generation and load demand, time series predictive modeling has been one of the key tools to guide the optimal decision-making for planning and operation. One of the critical challenges of time series renewable energy forecasting is the lack of historical data to train an adequate predictive model. Moreover, the performance of a machine learning model is sensitive to the cho…
Stanford University（斯坦福大学）；AWS AI Labs（AWS人工智能实验室）
Meta-forecasting is a newly emerging field which combines meta-learning and time series forecasting. The goal of meta-forecasting is to train over a collection of source time series and generalize to new time series one-at-a-time. Previous approaches in meta-forecasting achieve competitive performance, but with the restriction of training a separate model for each sampling frequency. In this work, we investigate meta-forecasting over different sampling frequencies, and introduce a new model, the Continuous Frequency Adapter (CFA), specifically designed to learn frequency-invariant representati…
FAF: A Feature-Adaptive Framework for Few-Shot Time Series Forecasting
The School of Computer and Artificial Intelligence of Zhengzhou University（郑州大学计算机与人工智能学院）；Engineering Research Center of Intelligent Swarm Systems, Ministry of Education（智能群体系统工程研究中心）；National Supercomputing Center In Zhengzhou（郑州国家超级计算中心）；New quality Software Engineering Research Center（高质量软件工程研究中心）
Prediction and Causality of functional MRI and synthetic signal using a Zero-Shot Time-Series Foundation Model
AGH University of Krakow, Poland（克拉科夫AGH大学）；Institut de Neurosciences de la Timone UMR 7289, Aix Marseille Université, CNRS, 13005, Marseille, France（里莫内神经科学研究所）
IIT（意大利理工学院）；UCL（伦敦大学学院）；Amazon Web Services（亚马逊云服务）
While classical time series forecasting considers individual time series in isolation, recent advances based on deep learning showed that jointly learning from a large pool of related time series can boost the forecasting accuracy. However, the accuracy of these methods suffers greatly when modeling out-of-sample time series, significantly limiting their applicability compared to classical forecasting methods. To bridge this gap, we adopt a meta-learning view of the time series forecasting problem. We introduce a novel forecasting method, called Meta Global-Local Auto-Regression (Meta-GLAR), t…
Gaussian Process Latent Variable Modeling for Few-shot Time Series Forecasting
Department of Computer Science, Aalborg University（奥尔堡大学计算机科学系）；Department of Computer Science, East China Normal University（华东师范大学计算机科学系）；Huawei Cloud Database Innovation Lab（华为云数据库创新实验室）；University of Electronic Science and Technology of China（电子科技大学）
Zero-shot Load Forecasting for Integrated Energy Systems: A Large Language Model-based Framework with Multi-task Learning
School of Automation Science and Engineering, Xi’an Jiaotong University（西安交通大学自动化科学与工程学院）；School of Electronic Information Engineering, Shanghai Dianji University（上海电机学院电子信息工程学院）；School of Energy and Power Engineering, Xi'an Jiaotong University（西安交通大学能源与动力工程学院）；Eindhoven University of Technology（埃因霍温理工大学）；School of Microelectronics, Xi’an Jiaotong University（西安交通大学微电子学院）；State Key Laboratory for Manufacturing System Engineering Lab, Xi’an Jiaotong University（西安交通大学制造系统工程国家重点实验室）
ROAR: Retrieval Opportunity-Aware Refinement for Zero-Shot Time Series Forecasting
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算机与数据科学学院）；City St George’s, University of London（伦敦大学城圣乔治学院）；Systems Research Institute, Polish Academy of Sciences（波兰科学院系统研究所）
Kaunas University of Technology（考纳斯理工大学）；Rivile（Rivile私人有限责任公司）
Amounts of historical data collected increase and business intelligence applicability with automatic forecasting of time series are in high demand. While no single time series modeling method is universal to all types of dynamics, forecasting using an ensemble of several methods is often seen as a compromise. Instead of fixing ensemble diversity and size, we propose to predict these aspects adaptively using meta-learning. Meta-learning here considers two separate random forest regression models, built on 390 time-series features, to rank 22 univariate forecasting methods and recommend ensemble…
The Chinese University of Hongkong, Shenzhen（香港中文大学（深圳））
While the advanced machine learning algorithms are effective in load forecasting, they often suffer from low data utilization, and hence their superior performance relies on massive datasets. This motivates us to design machine learning algorithms with improved data utilization. Specifically, we consider the load forecasting for a new user in the system by observing only few shots (data points) of its energy consumption. This task is challenging since the limited samples are insufficient to exploit the temporal characteristics, essential for load forecasting. Nonetheless, we notice that there …
TimeFound: A Foundation Model for Time Series Forecasting
Baidu Research（百度研究院）；University of Science and Technology of China（中国科学技术大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Meta-learning and Data Augmentation for Stress Testing Forecasting Models
Faculdade de Engenharia da Universidade do Porto（波尔图大学工程学院）；Laboratory for Artificial Intelligence and Computer Science (LIACC)（人工智能与计算机科学实验室（LIACC））；Fraunhofer Portugal AICOS（弗劳恩霍夫葡萄牙AICOS研究所）
The contribution of this work is twofold: (1) We introduce a collection of ensemble methods for time series forecasting to combine predictions from base models. We demonstrate insights on the power of ensemble learning for forecasting, showing experiment results on about 16000 openly available datasets, from M4, M5, M3 competitions, as well as FRED (Federal Reserve Economic Data) datasets. Whereas experiments show that ensembles provide a benefit on forecasting results, there is no clear winning ensemble strategy (plus hyperparameter configuration). Thus, in addition, (2), we propose a meta-le…
