中文
相关论文

相关论文: Learn over Past, Evolve for Future: Forecasting Te…

200 篇论文

Large language models (LLMs) exhibit remarkable capabilities in question answering and reasoning thanks to their extensive parametric memory. However, their knowledge is inherently limited by the scope of their pre-training data, while…

计算与语言 · 计算机科学 2025-06-10 Atahan Özer , Çağatay Yıldız

Recent lightweight MLP-based models have achieved strong performance in time series forecasting by capturing stable trends and seasonal patterns. However, their effectiveness hinges on an implicit assumption of local stationarity…

机器学习 · 计算机科学 2026-01-29 Zhiyu Chen , Minhao Liu , Yanru Zhang

Long-term time series forecasting is critical in domains such as finance, economics, and energy, where accurate and reliable predictions over extended horizons drive strategic decision-making. Despite the progress in machine learning-based…

机器学习 · 计算机科学 2025-02-18 Aditya Dey , Jonas Kusch , Fadi Al Machot

The proliferation of fake news has emerged as a significant threat to the integrity of information dissemination, particularly on social media platforms. Misinformation can spread quickly due to the ease of creating and disseminating…

The objective of this work is to improve the accuracy of building demand forecasting. This is a more challenging task than grid level forecasting. For the said purpose, we develop a new technique called recurrent transform learning (RTL).…

机器学习 · 计算机科学 2019-12-12 Megha Gupta , Angshul Majumdar

Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Zishu Zhou , Zaipeng Xie , Xuanyao Jie

Time Series Forecasting plays a crucial role in various fields such as industrial equipment maintenance, meteorology, energy consumption, traffic flow and financial investment. However, despite their considerable advantages over traditional…

机器学习 · 计算机科学 2024-07-02 Ruiqi Li , Maowei Jiang , Kai Wang , Kaiduo Feng , Quangao Liu , Yue Sun , Xiufang Zhou

The ability to accurately comprehend natural language instructions and navigate to the target location is essential for an embodied agent. Such agents are typically required to execute user instructions in an online manner, leading us to…

计算机视觉与模式识别 · 计算机科学 2024-05-21 Junyu Gao , Xuan Yao , Changsheng Xu

Data in the real world often has an evolving distribution. Thus, machine learning models trained on such data get outdated over time. This phenomenon is called model drift. Knowledge of this drift serves two purposes: (i) Retain an accurate…

机器学习 · 计算机科学 2025-03-11 Pranoy Panda , Kancheti Sai Srinivas , Vineeth N Balasubramanian , Gaurav Sinha

New events emerge over time influencing the topics of rumors in social media. Current rumor detection benchmarks use random splits as training, development and test sets which typically results in topical overlaps. Consequently, models…

计算与语言 · 计算机科学 2023-02-08 Yida Mu , Kalina Bontcheva , Nikolaos Aletras

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available…

计算机视觉与模式识别 · 计算机科学 2022-10-17 Yongyi Su , Xun Xu , Kui Jia

The creation of news timeline is essential for a comprehensive and contextual understanding of events as they unfold over time. This approach aids in discerning patterns and trends that might be obscured when news is viewed in isolation. By…

人工智能 · 计算机科学 2023-11-21 Sha Wang , Yuchen Li , Hanhua Xiao , Lambert Deng , Yanfei Dong

Online video understanding often relies on individual frames, leading to frame-by-frame predictions. Recent advancements such as Online Temporal Action Localization (OnTAL), extend this approach to instance-level predictions. However,…

计算机视觉与模式识别 · 计算机科学 2024-08-14 Sakib Reza , Yuexi Zhang , Mohsen Moghaddam , Octavia Camps

Fake news detection research is still in the early stage as this is a relatively new phenomenon in the interest raised by society. Machine learning helps to solve complex problems and to build AI systems nowadays and especially in those…

计算与语言 · 计算机科学 2022-01-20 Sajjad Ahmed , Knut Hinkelmann , Flavio Corradini

Over the past few years, there has been a substantial effort towards automated detection of fake news on social media platforms. Existing research has modeled the structure, style, content, and patterns in dissemination of online posts, as…

Evaluating robustness under temporal distribution shift remains an open challenge. Existing metrics quantify the average decline in performance, but fail to capture how models adapt to evolving data. As a result, temporal degradation is…

机器学习 · 计算机科学 2026-04-09 Lorenzo Iovine , Giacomo Ziffer , Emanuele Della Valle

Deep classifiers may encounter significant performance degradation when processing unseen testing data from varying centers, vendors, and protocols. Ensuring the robustness of deep models against these domain shifts is crucial for their…

计算机视觉与模式识别 · 计算机科学 2023-06-06 Yuhao Huang , Xin Yang , Xiaoqiong Huang , Xinrui Zhou , Haozhe Chi , Haoran Dou , Xindi Hu , Jian Wang , Xuedong Deng , Dong Ni

Techniques for clustering student behaviour offer many opportunities to improve educational outcomes by providing insight into student learning. However, one important aspect of student behaviour, namely its evolution over time, can often…

机器学习 · 计算机科学 2021-10-08 Jessica McBroom , Kalina Yacef , Irena Koprinska

Temporal graph clustering is a complex task that involves discovering meaningful structures in dynamic graphs where relationships and entities change over time. Existing methods typically require centralized data collection, which poses…

机器学习 · 计算机科学 2025-03-04 Zihao Zhou , Yang Liu , Xianghong Xu , Qian Li

Traditional vision-based autonomous driving systems often face difficulties in navigating complex environments when relying solely on single-image inputs. To overcome this limitation, incorporating temporal data such as past image frames or…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Tuong Do , Binh X. Nguyen , Quang D. Tran , Erman Tjiputra , Te-Chuan Chiu , Anh Nguyen