中文
相关论文

相关论文: MEMTS: Internalizing Domain Knowledge via Paramete…

200 篇论文

Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training, but adapting them to downstream domains under distribution shift remains challenging. Existing solutions face a trade-off:…

Time series forecasting (TSF) plays a critical role in decision-making for many real-world applications. Recently, LLM-based forecasters have made promising advancements. Despite their effectiveness, existing methods often lack explicit…

机器学习 · 计算机科学 2026-02-04 Xiaoyu Tao , Mingyue Cheng , Ze Guo , Shuo Yu , Yaguo Liu , Qi Liu , Shijin Wang

Time Series Foundation Models (TSFMs) have shown promising zero-shot generalization across diverse forecasting tasks. However, their robustness to continual adaptation remains underexplored. In this work, we investigate the extent to which…

机器学习 · 计算机科学 2025-10-03 Nouha Karaouli , Denis Coquenet , Elisa Fromont , Martial Mermillod , Marina Reyboz

Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity. While recent efforts are focused on building such FMs by unlocking the potential…

机器学习 · 计算机科学 2024-10-10 Qingxiang Liu , Xu Liu , Chenghao Liu , Qingsong Wen , Yuxuan Liang

Multi-task and few-shot time series forecasting tasks are commonly encountered in scenarios such as the launch of new products in different cities. However, traditional time series forecasting methods suffer from insufficient historical…

机器学习 · 计算机科学 2025-06-25 Pengpeng Ouyang , Dong Chen , Tong Yang , Shuo Feng , Zhao Jin , Mingliang Xu

Despite recent progress in time-series foundation models, challenges persist in improving representation learning and adapting to diverse downstream tasks. We introduce a General Time-series Model (GTM), which advances representation…

机器学习 · 计算机科学 2026-03-13 Cheng He , Xu Huang , Gangwei Jiang , Zhaoyi Li , Defu Lian , Hong Xie , Enhong Chen , Xijie Liang , Zengrong Zheng , Patrick P. C. Lee

Recently reconstruction-based deep models have been widely used for time series anomaly detection, but as their capacity and generalization capability increase, these models tend to over-generalize, often reconstructing unseen anomalies…

机器学习 · 计算机科学 2026-01-30 Samuel Yoon , Jongwon Kim , Juyoung Ha , Young Myoung Ko

Process Model Forecasting (PMF) aims to predict how the control-flow structure of a process evolves over time by modeling the temporal dynamics of directly-follows (DF) relations, complementing predictive process monitoring that focuses on…

机器学习 · 计算机科学 2025-12-09 Yongbo Yu , Jari Peeperkorn , Johannes De Smedt , Jochen De Weerdt

Time Series Foundation Models (TSFMs) advance generalization and data efficiency in time series forecasting by unified large-scale pretraining. But TSFMs remain lacking when adapting to specific downstream forecasting tasks for two reasons.…

信号处理 · 电气工程与系统科学 2026-05-04 Siyang Li , Yize Chen , Zijie Zhu , Yuxin Pan , Yan Guo , Ming Huang , Hui Xiong

Web platforms, mobile applications, and connected sensing systems generate multivariate time series with states at multiple levels of granularity, from coarse regimes to fine-grained events. Effective segmentation in these settings requires…

机器学习 · 计算机科学 2025-10-14 Ching Chang , Ming-Chih Lo , Chiao-Tung Chan , Wen-Chih Peng , Tien-Fu Chen

Forecasting Multivariate Time Series (MTS) involves significant challenges in various application domains. One immediate challenge is modeling temporal patterns with the finite length of the input. These temporal patterns usually involve…

机器学习 · 计算机科学 2024-09-30 Muyao Wang , Wenchao Chen , Zhibin Duan , Bo Chen

Large time series models (LTMs) have emerged as powerful tools for universal forecasting, yet they often struggle with the inherent diversity and nonstationarity of real-world time series data, leading to an unsatisfactory trade-off between…

机器学习 · 计算机科学 2026-03-03 Yunzhong Qiu , Zhiyao Cen , Zhongyi Pei , Chen Wang , Jianmin Wang

The Transformer-based detectors (i.e., DETR) have demonstrated impressive performance on end-to-end object detection. However, transferring DETR to different data distributions may lead to a significant performance degradation. Existing…

计算机视觉与模式识别 · 计算机科学 2023-07-04 Peidong Jia , Jiaming Liu , Senqiao Yang , Jiarui Wu , Xiaodong Xie , Shanghang Zhang

Pre-trained foundation models (FMs) have shown exceptional performance in univariate time series forecasting tasks. However, several practical challenges persist, including managing intricate dependencies among features and quantifying…

Forecasting complex time series is an important yet challenging problem that involves various industrial applications. Recently, masked time-series modeling has been proposed to effectively model temporal dependencies for forecasting by…

机器学习 · 计算机科学 2025-07-02 Hyunwoo Seo , Chiehyeon Lim

Large Language Models (LLMs) and Foundation Models (FMs) have recently become prevalent for time series forecasting tasks. While fine-tuning LLMs enables domain adaptation, they often struggle to generalize across diverse and unseen…

Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training, yet fine-tuning remains critical for boosting performance in domains with limited public data. With the growing number of TSFMs,…

机器学习 · 计算机科学 2025-09-30 Qingren Yao , Ming Jin , Chengqi Zhang , Chao-Han Huck Yang , Jun Qi , Shirui Pan

Universal domain adaptation aims to align the classes and reduce the feature gap between the same category of the source and target domains. The target private category is set as the unknown class during the adaptation process, as it is not…

计算机视觉与模式识别 · 计算机科学 2024-02-07 Yuxiang Lai , Yi Zhou , Xinghong Liu , Tao Zhou

The non-stationary nature of real-world Multivariate Time Series (MTS) data presents forecasting models with a formidable challenge of the time-variant distribution of time series, referred to as distribution shift. Existing studies on the…

机器学习 · 计算机科学 2024-07-19 Hui He , Qi Zhang , Kun Yi , Xiaojun Xue , Shoujin Wang , Liang Hu , Longbing Cao

Time series foundation models have shown impressive performance on a variety of tasks, across a wide range of domains, even in zero-shot settings. However, most of these models are designed to handle short univariate time series as an…

机器学习 · 计算机科学 2024-09-23 Nina Żukowska , Mononito Goswami , Michał Wiliński , Willa Potosnak , Artur Dubrawski
‹ 上一页 1 2 3 10 下一页 ›