Hyperparameter optimization (HPO) plays a central role in the performance of deep learning models, yet remains computationally expensive and difficult to interpret, particularly for time-series forecasting. While Bayesian Optimization (BO) is a standard approach, it typically treats tuning tasks independently and provides limited insight into its decisions. Recent advances in large language models (LLMs) offer new opportunities to incorporate structured prior knowledge and reasoning into optimization pipelines. We introduce LLM-AutoOpt, a hybrid HPO framework that combines BO with LLM-based contextual reasoning. The framework encodes dataset meta-features, model descriptions, historical optimization outcomes, and target objectives as structured meta-knowledge within LLM prompts, using BO to initialize the search and mitigate cold-start effects. This design enables context-aware and stable hyperparameter refinement while exposing the reasoning behind optimization decisions. Experiments on a multivariate time series forecasting benchmark demonstrate that LLM-AutoOpt achieves improved predictive performance and more interpretable optimization behavior compared to BO and LLM baselines without meta-knowledge.
Sensors in cyber-physical systems often capture interconnected processes and thus emit correlated time series (CTS), the forecasting of which enables important applications. The key to successful CTS forecasting is to uncover the temporal dynamics of time series and the spatial correlations among time series. Deep learning-based solutions exhibit impressive performance at discerning these aspects. In particular, automated CTS forecasting, where the design of an optimal deep learning architecture is automated, enables forecasting accuracy that surpasses what has been achieved by manual approach…
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…
Sliding-Window Reordering with Overlap Averaging: A Simple Time-Domain Augmentation for Multivariate Forecasting
Data Science Group, University of Hildesheim（希尔德斯海姆大学数据科学组）；Information Systems and Machine Learning Lab (ISMLL), University of Hildesheim（希尔德斯海姆大学信息系统与机器学习实验室）
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…
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…
CATS-Linear: Classification Auxiliary Linear Model for Time Series Forecasting
School of Science, Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳）科学学院）；Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳））；University of Lille, France（里尔大学）；School of Science, Great Bay University, Dongguan, China（东莞大湾大学科学学院）
Streamlining Ocean Dynamics Modeling with Fourier Neural Operators: A Multiobjective Hyperparameter and Architecture Optimization Approach
Argonne National Laboratory（阿贡国家实验室）；Florida State University（佛罗里达州立大学）；Université Paris-Saclay（巴黎萨克雷大学）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Oak Ridge National Laboratory（橡树岭国家实验室）
Time series forecasting with Gaussian Processes needs priors
Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA)（达莱莫勒人工智能研究所（IDSIA））；USI - SUPSI（瑞士意大利语区大学-瑞士南部应用科学与艺术大学）；Trinity College Dublin（都柏林圣三一学院）
针对 GP 自动预测中的核选择与超参数估计问题，提出固定核组合、ARD 自动剪枝及经验贝叶斯先验，在多类时间序列上提升精度并实现单次重启快速训练。
Multivariate time series prediction has attracted a lot of attention because of its wide applications such as intelligence transportation, AIOps. Generative models have achieved impressive results in time series modeling because they can model data distribution and take noise into consideration. However, many existing works can not be widely used because of the constraints of functional form of generative models or the sensitivity to hyperparameters. In this paper, we propose ScoreGrad, a multivariate probabilistic time series forecasting framework based on continuous energy-based generative m…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；RWTH Aachen University（亚琛工业大学）；Forschungszentrum Jülich GmbH（于利希研究中心有限公司）
Time series forecasting is fundamental for various use cases in different domains such as energy systems and economics. Creating a forecasting model for a specific use case requires an iterative and complex design process. The typical design process includes the five sections (1) data pre-processing, (2) feature engineering, (3) hyperparameter optimization, (4) forecasting method selection, and (5) forecast ensembling, which are commonly organized in a pipeline structure. One promising approach to handle the ever-growing demand for time series forecasts is automating this design process. The p…
Leibniz University Hannover（汉诺威莱布尼茨大学）；Ludwig-Maximilian University（路德维希-马克西米利安大学）；Fraunhofer Institute for Integrated Circuits (IIS)（弗劳恩霍夫集成电路研究所）；University of Freiburg（弗莱堡大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）
Recent years have witnessed tremendously improved efficiency of Automated Machine Learning (AutoML), especially Automated Deep Learning (AutoDL) systems, but recent work focuses on tabular, image, or NLP tasks. So far, little attention has been paid to general AutoDL frameworks for time series forecasting, despite the enormous success in applying different novel architectures to such tasks. In this paper, we propose an efficient approach for the joint optimization of neural architecture and hyperparameters of the entire data processing pipeline for time series forecasting. In contrast to commo…
Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting
Southern University of Science and Technology（南方科技大学）；The University of Tokyo（东京大学）；Hong Kong University of Science and Technology（香港科技大学）；Squirrel AI（松鼠AI）；Jilin University（吉林大学）
CoRe: Coherence and Relational Alignment for Multivariate Time Series Forecasting
College of Computer and Information Technology, China Three Gorges University（三峡大学计算机与信息学院）；City University of New York（纽约城市大学）；University of California, Berkeley（加州大学伯克利分校）；Emory University（埃默里大学）
Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms without any RNN can improve on the results in various sequence processing tasks (e.g. NLP). Multiple studies since then have shown that similar approaches can be applied for images, point clouds, video, audio or time series forecasting. Furthermore, solutions such as the Perceiver or the Informer have been introduced to expand on the applicability of the Tra…
Auto-Configured Networks for Multi-Scale Multi-Output Time-Series Forecasting
National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University（东北大学工业智能与系统优化国家级前沿科学中心）；Innovative Artificial Intelligence Cluster, Digital Future Institute, De Montfort University（德蒙福特大学数字未来研究所创新人工智能集群）；Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University), Ministry of Education（教育部智能工业数据解析与优化重点实验室（东北大学））
Institute for Intelligent Systems（智能系统研究所）；University of Johannesburg（约翰内斯堡大学）
Meta-learning, decision fusion, hybrid models, and representation learning are topics of investigation with significant traction in time-series forecasting research. Of these two specific areas have shown state-of-the-art results in forecasting: hybrid meta-learning models such as Exponential Smoothing - Recurrent Neural Network (ES-RNN) and Neural Basis Expansion Analysis (N-BEATS) and feature-based stacking ensembles such as Feature-based FORecast Model Averaging (FFORMA). However, a unified taxonomy for model fusion and an empirical comparison of these hybrid and feature-based stacking ense…
Dalian University of Technology（大连理工大学）；Microsoft Research（微软研究院）；LinkedIn Corporation（领英公司）
User engagement prediction plays a critical role for designing interaction strategies to grow user engagement and increase revenue in online social platforms. Through the in-depth analysis of the real-world data from the world's largest professional social platforms, i.e., LinkedIn, we find that users expose diverse engagement patterns, and a major reason for the differences in user engagement patterns is that users have different intents. That is, people have different intents when using LinkedIn, e.g., applying for jobs, building connections, or checking notifications, which shows quite diff…
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）
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…
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 i…
CWI Amsterdam, the Netherlands（荷兰阿姆斯特丹数学与计算机科学研究院）
In this paper we study the generalization capabilities of fully-connected neural networks trained in the context of time series forecasting. Time series do not satisfy the typical assumption in statistical learning theory of the data being i.i.d. samples from some data-generating distribution. We use the input and weight Hessians, that is the smoothness of the learned function with respect to the input and the width of the minimum in weight space, to quantify a network's ability to generalize to unseen data. While such generalization metrics have been studied extensively in the i.i.d. setting …
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 University of Tokyo（东京大学）；Toyota Motor Corporation（丰田汽车公司）
Traffic forecasting as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the spatio-temporal heterogeneity and non-stationarity implied in the traffic stream, in this study, we propose Spatio-Temporal Meta-Graph Learning as a novel Graph Structure Learning mechanism on spatio-temporal data. Specifically, we implement this idea into Meta-Graph Convolutional Recurrent Network (MegaCRN) by plugging the Meta-Graph Learner powered by a Meta-Node Bank into GCRN encoder-decoder. We conduct a comprehensive evaluation on two bench…
Massachusetts Institute of Technology（麻省理工学院）；Argonne National Laboratory（阿贡国家实验室）
Accurately forecasting the weather is a key requirement for climate change mitigation. Data-driven methods offer the ability to make more accurate forecasts, but lack interpretability and can be expensive to train and deploy if models are not carefully developed. Here, we make use of two historical climate data sets and tools from machine learning, to accurately predict temperature fields. Furthermore, we are able to use low fidelity models that are cheap to train and evaluate, to selectively avoid expensive high fidelity function evaluations, as well as uncover seasonal variations in predicti…
In this work, we highlight our novel evolutionary sparse time-series forecasting algorithm also known as EvoSTS. The algorithm attempts to evolutionary prioritize weights of Long Short-Term Memory (LSTM) Network that best minimize the reconstruction loss of a predicted signal using a learned sparse coded dictionary. In each generation of our evolutionary algorithm, a set number of children with the same initial weights are spawned. Each child undergoes a training step and adjusts their weights on the same data. Due to stochastic back-propagation, the set of children has a variety of weights wi…
University of the Witwatersrand（金山大学）；University of Johannesburg（约翰内斯堡大学）
Hybrid methods have been shown to outperform pure statistical and pure deep learning methods at forecasting tasks and quantifying the associated uncertainty with those forecasts (prediction intervals). One example is Exponential Smoothing Recurrent Neural Network (ES-RNN), a hybrid between a statistical forecasting model and a recurrent neural network variant. ES-RNN achieves a 9.4\% improvement in absolute error in the Makridakis-4 Forecasting Competition. This improvement and similar outperformance from other hybrid models have primarily been demonstrated only on univariate datasets. Difficu…
University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）；Northwestern University Feinberg School of Medicine（西北大学范伯格医学院）
COVID-19 has been a public health emergency of international concern since early 2020. Reliable forecasting is critical to diminish the impact of this disease. To date, a large number of different forecasting models have been proposed, mainly including statistical models, compartmental models, and deep learning models. However, due to various uncertain factors across different regions such as economics and government policy, no forecasting model appears to be the best for all scenarios. In this paper, we perform quantitative analysis of COVID-19 forecasting of confirmed cases and deaths across…
Simula Research Laboratory（Simula研究实验室）；University of Thessaly（色萨利大学）；University of Oslo（奥斯陆大学）；Simula Metropolitan（Simula大都会中心）
Bandwidth forecasting in Mobile Broadband (MBB) networks is a challenging task, particularly when coupled with a degree of mobility. In this work, we introduce HINDSIGHT++, an open-source R-based framework for bandwidth forecasting experimentation in MBB networks with Long Short Term Memory (LSTM) networks. We instrument HINDSIGHT++ following an Automated Machine Learning (AutoML) paradigm to first, alleviate the burden of data preprocessing, and second, enhance performance related aspects. We primarily focus on bandwidth forecasting for Fifth Generation (5G) networks. In particular, we levera…
University of Alberta（阿尔伯塔大学）；University of Hradec Králové（赫拉德茨-克拉洛韦大学）
Electrical load prediction has become an integral part of power system operation. Deep learning models have found popularity for this purpose. However, to achieve a desired prediction accuracy, they require huge amounts of data for training. Sharing electricity consumption data of individual households for load prediction may compromise user privacy and can be expensive in terms of communication resources. Therefore, edge computing methods, such as federated learning, are gaining more importance for this purpose. These methods can take advantage of the data without centrally storing it. This p…
