551 citations · 847 across the 23 of their papers we have counts for
20 papers · 1 filter
Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling
Yang Zhao, Peisong Niu, Tian Zhou +5
The development of 0.1 global weather forecasting models based on machine learning (ML) is constrained by the limited availability of high-resolution data, as decades of…
Baguan-TS: A Sequence-Native In-Context Learning Model for Time Series Forecasting with Covariates
Linxiao Yang, Xue Jiang, Gezheng Xu +9
Transformers enable in-context learning (ICL) for rapid, gradient-free adaptation in time series forecasting, yet most ICL-style approaches rely on tabularized, hand-crafted featur…
Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
Yifan Hu, Jie Yang, Tian Zhou +4
Although contrastive and other representation-learning methods have long been explored in vision and NLP, their adoption in modern time series forecasters remains limited. We belie…
Utilizing Strategic Pre-training to Reduce Overfitting: Baguan -- A Pre-trained Weather Forecasting Model
Peisong Niu, Ziqing Ma, Tian Zhou +4
Weather forecasting has long posed a significant challenge for humanity. While recent AI-based models have surpassed traditional numerical weather prediction (NWP) methods in globa…
Maximizing the Impact of Deep Learning on Subseasonal-to-Seasonal Climate Forecasting: The Essential Role of Optimization
Yizhen Guo, Tian Zhou, Wanyi Jiang +3
Weather and climate forecasting is vital for sectors such as agriculture and disaster management. Although numerical weather prediction (NWP) systems have advanced, forecasting at…
Mitigating Time Discretization Challenges with WeatherODE: A Sandwich Physics-Driven Neural ODE for Weather Forecasting
Peiyuan Liu, Tian Zhou, Liang Sun +1
In the field of weather forecasting, traditional models often grapple with discretization errors and time-dependent source discrepancies, which limit their predictive performance.…
SAttention: Improving Long Sequence Attention with Smoothed Skeleton Sketching
Xue Wang, Tian Zhou, Jianqing Zhu +6
Attention based models have achieved many remarkable breakthroughs in numerous applications. However, the quadratic complexity of Attention makes the vanilla Attention based models…
Sparse-VQ Transformer: An FFN-Free Framework with Vector Quantization for Enhanced Time Series Forecasting
Yanjun Zhao, Tian Zhou, Chao Chen +3
Time series analysis is vital for numerous applications, and transformers have become increasingly prominent in this domain. Leading methods customize the transformer architecture…
FusionSF: Fuse Heterogeneous Modalities in a Vector Quantized Framework for Robust Solar Power Forecasting
Ziqing Ma, Wenwei Wang, Tian Zhou +4
Accurate solar power forecasting is crucial to integrate photovoltaic plants into the electric grid, schedule and secure the power grid safety. This problem becomes more demanding…
Attention as Robust Representation for Time Series Forecasting
PeiSong Niu, Tian Zhou, Xue Wang +2
Time series forecasting is essential for many practical applications, with the adoption of transformer-based models on the rise due to their impressive performance in NLP and CV. T…
Model-free Test Time Adaptation for Out-Of-Distribution Detection
YiFan Zhang, Xue Wang, Tian Zhou +5
Out-of-distribution (OOD) detection is essential for the reliability of ML models. Most existing methods for OOD detection learn a fixed decision criterion from a given in-distribu…
Understanding the Role of Textual Prompts in LLM for Time Series Forecasting: an Adapter View
Peisong Niu, Tian Zhou, Xue Wang +2
In the burgeoning domain of Large Language Models (LLMs), there is a growing interest in applying LLM to time series forecasting, with multiple studies focused on leveraging textua…
OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling
Yi-Fan Zhang, Qingsong Wen, Xue Wang +6
Online updating of time series forecasting models aims to address the concept drifting problem by efficiently updating forecasting models based on streaming data. Many algorithms a…
AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation
Yi-Fan Zhang, Xue Wang, Kexin Jin +5
Many recent machine learning tasks focus to develop models that can generalize to unseen distributions. Domain generalization (DG) has become one of the key topics in various field…
CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting
Wang Xue, Tian Zhou, Qingsong Wen +3
Recent studies have demonstrated the great power of Transformer models for time series forecasting. One of the key elements that lead to the transformer's success is the channel-in…
One Fits All:Power General Time Series Analysis by Pretrained LM
Tian Zhou, PeiSong Niu, Xue Wang +2
Although we have witnessed great success of pre-trained models in natural language processing (NLP) and computer vision (CV), limited progress has been made for general time series…
Free Lunch for Domain Adversarial Training: Environment Label Smoothing
YiFan Zhang, Xue Wang, Jian Liang +4
A fundamental challenge for machine learning models is how to generalize learned models for out-of-distribution (OOD) data. Among various approaches, exploiting invariant features…
TreeDRNet:A Robust Deep Model for Long Term Time Series Forecasting
Tian Zhou, Jianqing Zhu, Xue Wang +4
Various deep learning models, especially some latest Transformer-based approaches, have greatly improved the state-of-art performance for long-term time series forecasting.However,…
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting
Tian Zhou, Ziqing Ma, Xue wang +5
Recent studies have shown that deep learning models such as RNNs and Transformers have brought significant performance gains for long-term forecasting of time series because they e…
FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
Tian Zhou, Ziqing Ma, Qingsong Wen +3
Although Transformer-based methods have significantly improved state-of-the-art results for long-term series forecasting, they are not only computationally expensive but more impor…