Transferable Time Series

Transferable time series analysis focuses on developing models that can accurately predict or classify time-series data across different domains, even with variations in data characteristics or limited labeled target data. Current research emphasizes techniques like cross-domain pre-training, leveraging language model architectures, and adversarial domain adaptation to learn domain-invariant representations and mitigate negative transfer. These advancements are improving the accuracy and generalizability of time-series models in diverse applications, such as demand forecasting, traffic prediction, and even the analysis of complex systems like transition metal complexes. The resulting models offer significant potential for improved efficiency and robustness in various fields.

Papers

April 26, 2024

Adversarial Reweighting with $\alpha$-Power Maximization for Domain Adaptation
Xiang Gu, Xi Yu, Yan Yang, Jian Sun, Zongben Xu
Domain Adaptation Transferable Time Series Optimal Power Adversarial Reweighting

March 19, 2024

Cross-Domain Pre-training with Language Models for Transferable Time Series Representations
Mingyue Cheng, Xiaoyu Tao, Qi Liu, Hao Zhang, Yiheng Chen, Defu Lian
Language Model Supervised Learning Cross Domain Transferable Representation Transferable Time Series

February 29, 2024

A Scalable and Transferable Time Series Prediction Framework for Demand Forecasting
Young-Jin Park, Donghyun Kim, Frédéric Odermatt, Juho Lee, Kyung-Min Kim
Time Series Forecasting Forecasting Model Demand Forecasting Transferable Time Series Visual Forecasting

July 31, 2023

Transferable Decoding with Visual Entities for Zero-Shot Image Captioning
Junjie Fei, Teng Wang, Jinrui Zhang, Zhenyu He, Chengjie Wang, Feng Zheng
Zero Shot Pre Trained Vision Language Model Caption Generation Visual Entity Image to Text Generation Transferable Time Series

February 2, 2023

Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network
Wendong Bi, Bingbing Xu, Xiaoqian Sun, Li Xu, Huawei Shen, Xueqi Cheng
Representation Learning Graph Drawing Node Representation Learning Transferable Graph Neural Transferable Time Series

May 5, 2022

Exploiting Ligand Additivity for Transferable Machine Learning of Multireference Character Across Known Transition Metal Complex Ligands
Chenru Duan, Adriana J. Ladera, Julian C. -L. Liu, Michael G. Taylor, Isuru R. Ariyarathna, Heather J. Kulik
Novel Ligand Transition Metal Transferable Time Series Molecular Machine

February 8, 2022

Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities
Yihong Tang, Ao Qu, Andy H. F. Chow, William H. K. Lam, S. C. Wong, Wei Ma
Urban Environment Task Transferability Traffic Forecasting Internet Service Domain Accurate Traffic Prediction Accurate Traffic Forecasting Short Term Traffic Network Wide Traffic Transferable Time Series

November 5, 2021

Transferable Time-Series Forecasting under Causal Conditional Shift
Zijian Li, Ruichu Cai, Tom Z. J Fu, Zhifeng Hao, Kun Zhang
Semi Supervised Domain Adaptation Time Series Domain Adaptation Conditional Shift Transferable Time Series

Transferable Time Series

Papers

Adversarial Reweighting with $\alpha$-Power Maximization for Domain Adaptation

Cross-Domain Pre-training with Language Models for Transferable Time Series Representations

A Scalable and Transferable Time Series Prediction Framework for Demand Forecasting

Transferable Decoding with Visual Entities for Zero-Shot Image Captioning

Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network

Exploiting Ligand Additivity for Transferable Machine Learning of Multireference Character Across Known Transition Metal Complex Ligands

Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities

Transferable Time-Series Forecasting under Causal Conditional Shift