Real-world time series are governed by both recurring structures, such as trends and seasonality, and infrequent yet critical variations, such as abrupt shifts and rare events. However, existing methods often lack an explicit mechanism to organize and utilize these heterogeneous patterns according to their distinct forecasting roles. Consequently, common and rare patterns can become entangled, preventing models from dynamically distinguishing and selectively leveraging them according to context. To address this issue, we propose Dual-Prototype Adaptive Disentanglement (DPAD), a model-agnostic framework that organizes temporal patterns by their forecasting roles. Specifically, we construct a Dynamic Dual-Prototype bank (DDP), comprising a common pattern bank initialized with structured temporal priors to represent prevalent dynamics, and a rare bank that adaptively memorizes infrequent deviations. Then a Dual-Path Context-aware routing (DPC) mechanism enhances outputs with selectively retrieved context-specific pattern representations from DDP. A Disentanglement-Guided Loss (DGLoss) is further introduced to ensure that each prototype bank specializes in its designated role while maintaining sufficient coverage. Extensive experiments across diverse real-world benchmarks demonstrate that DPAD consistently improves the forecasting performance of a range of time-series models.
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）
Stock trend forecasting has become a popular research direction that attracts widespread attention in the financial field. Though deep learning methods have achieved promising results, there are still many limitations, for example, how to extract clean features from the raw stock data. In this paper, we introduce an \emph{Augmented Disentanglement Distillation (ADD)} approach to remove interferential features from the noised raw data. Specifically, we present 1) a disentanglement structure to separate excess and market information from the stock data to avoid the two factors disturbing each ot…
Time series forecasting has been a widely explored task of great importance in many applications. However, it is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series. In this work, we propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder (BVAE) equipped with diffusion, denoise, and disentanglement, namely D3VAE. Specifically, a coupled diffusion probabilistic model is proposed to augment the time series da…
Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecasting
School of Computer Science, Guangdong University of Technology（广东工业大学计算机学院）；Peng Cheng Laboratory（鹏城实验室）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Shantou University（汕头大学）
An Integrated Forecasting Prototype for Emergency Department Boarding Time to Support Proactive Operational Decision Making
Department of Electrical and Computer Engineering, University of Alabama at Birmingham（阿拉巴马大学伯明翰分校电气与计算机工程系）；Department of Health Services Administration, University of Alabama at Birmingham（阿拉巴马大学伯明翰分校卫生服务管理系）；Department of Biomedical Informatics and Data Science, Heersink School of Medicine, University of Alabama at Birmingham（阿拉巴马大学伯明翰分校希尔斯医院医学院生物医学信息学与数据科学系）；Department of Emergency Medicine, University of Alabama at Birmingham（阿拉巴马大学伯明翰分校急诊医学系）
Accurate and Efficient Multivariate Time Series Forecasting via Offline Clustering
State Key Laboratory of Complex & Critical Software Environment（复杂与关键软件环境国家重点实验室）；Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（未来区块链与隐私计算北京先进创新中心）；Beihang University（北京航空航天大学）；HKGAI（Hong Kong University of Science and Technology）；Research Institute of Trustworthy Autonomous Systems（可信自主系统研究 institute）；Southern University of Science and Technology（南方科技大学）；Department of Data Science（数据科学系）
Predefined Prototypes for Intra-Class Separation and Disentanglement
ViVoLab（维沃实验室）；Aragón Institute for Engineering Research (I3A)（阿拉贡工程研究所（I3A））；University of Zaragoza（萨拉戈萨大学）；LIUM（勒芒大学集成与多媒体实验室）；Le Mans University（勒芒大学）；LTCI（通信与集成实验室）；Télécom Paris（巴黎电信学院）；Institut Polytechnique de Paris（巴黎综合理工学院）
PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting
College of Computer Science, Sichuan University, Chengdu, China（四川大学计算机学院）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（中国科学院计算技术研究所）；Institute of Artificial Intelligence, University of Central Florida, Orlando, USA（佛罗里达大学人工智能研究所）
TU Darmstadt（达姆施塔特工业大学）；Hessian Center for AI (hessian.AI)（黑森人工智能中心（hessian.AI））；Centre for Cognitive Science, TU Darmstadt（达姆施塔特工业大学认知科学中心）
Learning visual concepts from raw images without strong supervision is a challenging task. In this work, we show the advantages of prototype representations for understanding and revising the latent space of neural concept learners. For this purpose, we introduce interactive Concept Swapping Networks (iCSNs), a novel framework for learning concept-grounded representations via weak supervision and implicit prototype representations. iCSNs learn to bind conceptual information to specific prototype slots by swapping the latent representations of paired images. This semantically grounded and discr…
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
Monash University（莫纳什大学）；Ant Group（蚂蚁集团）；IBM Research（IBM研究院）；Griffith University（格里菲斯大学）；Alibaba Group（阿里巴巴集团）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Revisiting Identity and Spectra Dispersion in Media-Bridged Time Series Forecasting: Linking Multivariate Signals and Narrative Flows
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences（中国科学院大学先进交叉科学学院）；State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Intelligent Systems Engineering, Sun Yat-sen University（中山大学智能系统工程学院）；School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；College of Computer Science, Chongqing University（重庆大学计算机学院）
SPORT: Structure-Aware Prototype Disentanglement for Incomplete Multi-View Clustering
College of Computer and Cyberspace Security, Hebei Normal University（河北师范大学计算机与网络空间安全学院）；Department of Statistics and Data Science, Southern University of Science and Technology（南方科技大学统计与数据科学系）；Key Laboratory of Tibetan Information Processing, Ministry of Education, Qinghai Normal University（青海师范大学藏文信息处理教育部重点实验室）；School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）；State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）
Boosting MLPs with a Coarsening Strategy for Long-Term Time Series Forecasting
School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）；School of Biology & Basic Medical Science, Soochow University（苏州大学生物与基础医学院）；School of Physics and Information Technology, Shaanxi Normal University（陕西师范大学物理与信息技术学院）
During the COVID-19 pandemic, a significant effort has gone into developing ML-driven epidemic forecasting techniques. However, benchmarks do not exist to claim if a new AI/ML technique is better than the existing ones. The "covid-forecast-hub" is a collection of more than 30 teams, including us, that submit their forecasts weekly to the CDC. It is not possible to declare whether one method is better than the other using those forecasts because each team's submission may correspond to different techniques over the period and involve human interventions as the teams are continuously changing/tu…
Technische Universität Berlin（柏林工业大学）；University of Glasgow（格拉斯哥大学）
With increasingly more computation being shifted to the edge of the network, monitoring of critical infrastructures, such as intermediate processing nodes in autonomous driving, is further complicated due to the typically resource-constrained environments. In order to reduce the resource overhead on the network link imposed by monitoring, various methods have been discussed that either follow a filtering approach for data-emitting devices or conduct dynamic sampling based on employed prediction models. Still, existing methods are mainly requiring adaptive monitoring on edge devices, which dema…
Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Determining causal effects of temporal multi-intervention assists decision-making. Restricted by time-varying bias, selection bias, and interactions of multiple interventions, the disentanglement and estimation of multiple treatment effects from individual temporal data is still rare. To tackle these challenges, we propose a comprehensive framework of temporal counterfactual forecasting from an individual multiple treatment perspective (TCFimt). TCFimt constructs adversarial tasks in a seq2seq framework to alleviate selection and time-varying bias and designs a contrastive learning-based block…
Pre-training Epidemic Time Series Forecasters with Compartmental Prototypes
Emory University Department of Computer Science Atlanta GA USA（埃默里大学计算机科学系）；Emory University Rollins School of Public Health Atlanta GA USA（埃默里大学罗林斯公共卫生学院）；Emory University（埃默里大学）
The recent proliferation of real-world human mobility datasets has catalyzed geospatial and transportation research in trajectory prediction, demand forecasting, travel time estimation, and anomaly detection. However, these datasets also enable, more broadly, a descriptive analysis of intricate systems of human mobility. We formally define patterns of life analysis as a natural, explainable extension of online unsupervised anomaly detection, where we not only monitor a data stream for anomalies but also explicitly extract normal patterns over time. To learn patterns of life, we adapt Grow When…
GRAM: Correcting Frozen Time-Series Foundation Models via Graph-Retrieved Amplitude Memory
East China Normal University（华东师范大学）；Peking University（北京大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of the Chinese Academy of Sciences（中国科学院大学）
Scuola Normale Superiore（比萨高等师范学校）；Scuola Superiore Sant’Anna（圣安娜高等研究院）；University of Pisa（比萨大学）；National Research Council（国家研究委员会）
Cloud auto-scaling mechanisms are typically based on reactive automation rules that scale a cluster whenever some metric, e.g., the average CPU usage among instances, exceeds a predefined threshold. Tuning these rules becomes particularly cumbersome when scaling-up a cluster involves non-negligible times to bootstrap new instances, as it happens frequently in production cloud services. To deal with this problem, we propose an architecture for auto-scaling cloud services based on the status in which the system is expected to evolve in the near future. Our approach leverages on time-series forec…
Shandong University（山东大学）；Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University（山东大学-南洋理工大学联合人工智能研究中心（C-FAIR））；Lund University（隆德大学）；Nanyang Technological University（南洋理工大学）
Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in the absence of expert annotations. However, existing contrastive approaches generally treat each instance independently, which leads to false negative pairs that share the same semantics. To tackle this problem, we propose MHCCL, a Masked Hierarchical Cluster-wise Contrastive Learning model, which exploits semantic information obtained from the hierarchical …
MEMTS: Internalizing Domain Knowledge via Parameterized Memory for Retrieval-Free Domain Adaptation of Time Series Foundation Models
East China Normal University（东华师范大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Peking University（北京大学）；University of Chinese Academy of Sciences（中国科学院大学）
