paper-with-me

Papers

FIC-TSC: Learning Time Series Classification with Fisher Information Constraint

2025-05-09 · Xiwen Chen, Wenhui Zhu, Peijie Qiu, Hao Wang, Huayu Li, Zihan Li, Yalin Wang, Aristeidis Sotiras, Abolfazl Razi

Analyzing time series data is crucial to a wide spectrum of applications, including economics, online marketplaces, and human healthcare. In particular, time series classification plays an indispensable role in segmenting different phases in stock markets, predicting customer behavior, and classifying worker actions and engagement levels. These aspects contribute significantly to the advancement of automated decision-making and system optimization in real-world applications. However, there is a large consensus that time series data often suffers from domain shifts between training and test sets, which dramatically degrades the classification performance. Despite the success of (reversible) instance normalization in handling the domain shifts for time series regression tasks, its performance in classification is unsatisfactory. In this paper, we propose \textit{FIC-TSC}, a training framework for time series classification that leverages Fisher information as the constraint. We theoretically and empirically show this is an efficient and effective solution to guide the model converge toward flatter minima, which enhances its generalizability to distribution shifts. We rigorously evaluate our method on 30 UEA multivariate and 85 UCR univariate datasets. Our empirical results demonstrate the superiority of the proposed method over 14 recent state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2505.06114

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationTime SeriesTime Series ClassificationTime Series Regression

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

Hierarchical Fisher Kernels for Longitudinal Data

2008-12-01 · NeurIPS 2008 12 · Zhengdong Lu, Jeffrey Kaye, Todd K. Leen

We develop new techniques for time series classification based on hierarchical Bayesian generative models (called mixed-effect models) and the Fisher kernel derived from them. A key advantage of the new formulation is th…

General ClassificationTime SeriesTime Series AnalysisTime Series Classification

Fisher GAN

2017-05-26 · NeurIPS 2017 12 · Youssef Mroueh, Tom Sercu

Generative Adversarial Networks (GANs) are powerful models for learning complex distributions. Stable training of GANs has been addressed in many recent works which explore different metrics between distributions. In thi…

General Classification

On stabilizing the variance of dynamic functional brain connectivity time series

2016-04-13

Assessment of dynamic functional brain connectivity (dFC) based on fMRI data is an increasingly popular strategy to investigate temporal dynamics of the brain's large-scale network architecture. Current practice when der…

Time SeriesTime Series Analysis

MomentQuant: an even more minimalist interval method with linear time complexity for time series classification

2026-09-04 · Johann Faouzi arxiv

Time series data is very common in many real-world applications and in numerous domains, with increasing interest for automated information extraction using machine learning. One of these subfields is time series classif…

Time Series ClassificationInformation Extraction

Adaptive von Mises-Fisher Likelihood Loss for Supervised Deep Time Series Hashing

2025-09-23 · Juan Manuel Perez, Kevin Garcia, Brooklyn Berry, Dongjin Song 외 arxiv

Indexing time series by creating compact binary representations is a fundamental task in time series data mining. Recently, deep learning-based hashing methods have proven effective for indexing time series based on sema…

Representation Learning