paper-with-me

홈 › Papers

Addressing Distribution Shift in Time Series Forecasting with Instance Normalization Flows

2024-01-30 · Wei Fan, Shun Zheng, Pengyang Wang, Rui Xie, Jiang Bian, Yanjie Fu

Due to non-stationarity of time series, the distribution shift problem largely hinders the performance of time series forecasting. Existing solutions either fail for the shifts beyond simple statistics or the limited compatibility with forecasting models. In this paper, we propose a general decoupled formulation for time series forecasting, with no reliance on fixed statistics and no restriction on forecasting architectures. Then, we make such a formulation formalized into a bi-level optimization problem, to enable the joint learning of the transformation (outer loop) and forecasting (inner loop). Moreover, the special requirements of expressiveness and bi-direction for the transformation motivate us to propose instance normalization flows (IN-Flow), a novel invertible network for time series transformation. Extensive experiments demonstrate our method consistently outperforms state-of-the-art baselines on both synthetic and real-world data.

📄 PDF Abstract BibTeX arXiv:2401.16777

Code (0)

등록된 구현이 없습니다.

Tasks

Time SeriesTime Series Forecasting

Methods 이 논문이 사용한 방법론

Instance Normalization Instance Normalization (also known as contrast normalization) is a normalization layer where: $$ y_{tijk} = \frac{x_{tijk} - \mu_{ti}}{\sqrt{\sigma_{ti}^2 +…

Similar Papers 제목 키워드 기반

Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift

2025-10-16 · Zhiyuan Zhao, Haoxin Liu, B. Aditya Prakash arxiv

Time-series forecasting finds broad applications in real-world scenarios. Due to the dynamic nature of time series data, it is important for time-series forecasting models to handle potential distribution shifts over tim…

Time Series Forecasting

Performative Time-Series Forecasting

2023-10-09 · Zhiyuan Zhao, Alexander Rodriguez, B. Aditya Prakash

Time-series forecasting is a critical challenge in various domains and has witnessed substantial progress in recent years. Many real-life scenarios, such as public health, economics, and social applications, involve feed…

Time SeriesTime Series Forecasting

AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs

2026-01-19 · Ting Dang, Soumyajit Chatterjee, Hong Jia, Yu Wu 외 arxiv

Test time adaptation (TTA) has emerged as a promising solution to adapt pre-trained models to new, unseen data distributions using unlabeled target domain data. However, most TTA methods are designed for independent data…

Time Series Forecasting

Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworks

2022-02-22 · Wenying Duan, Xiaoxi He, Lu Zhou, Lothar Thiele 외

Time series forecasting has widespread applications in urban life ranging from air quality monitoring to traffic analysis. However, accurate time series forecasting is challenging because real-world time series suffer fr…

Domain AdaptationTime SeriesTime Series AnalysisTime Series Forecasting

Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shift

2024-07-18 · Hui He, Qi Zhang, Kun Yi, Xiaojun Xue 외

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. Exis…

Multivariate Time Series ForecastingTime SeriesTime Series Forecasting