Neural Fourier Modelling: A Highly Compact Approach to Time-Series Analysis
M Kim, Y Hioka, M Witbrock - arXiv preprint arXiv:2410.04703, 2024 - arxiv.org
Neural time-series analysis has traditionally focused on modeling data in the time domain,
often with some approaches incorporating equivalent Fourier domain representations as …
often with some approaches incorporating equivalent Fourier domain representations as …
Enhancing Representation Learning for Periodic Time Series with Floss: A Frequency Domain Regularization Approach
Time series analysis is a fundamental task in various application domains, and deep
learning approaches have demonstrated remarkable performance in this area. However …
learning approaches have demonstrated remarkable performance in this area. However …
FAN: Fourier Analysis Networks
Despite the remarkable success achieved by neural networks, particularly those
represented by MLP and Transformer, we reveal that they exhibit potential flaws in the …
represented by MLP and Transformer, we reveal that they exhibit potential flaws in the …
ATFNet: Adaptive Time-Frequency Ensembled Network for Long-term Time Series Forecasting
H Ye, J Chen, S Gong, F Jiang, T Zhang, J Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
The intricate nature of time series data analysis benefits greatly from the distinct advantages
offered by time and frequency domain representations. While the time domain is superior in …
offered by time and frequency domain representations. While the time domain is superior in …
GAFNO: Gated Adaptive Fourier Neural Operator for Task-Agnostic Time Series Modeling
XY Li, YB Yang - 2023 IEEE International Conference on Data …, 2023 - ieeexplore.ieee.org
Time series data is ubiquitous in various domains, making it crucial for numerous research
and practical applications. Previous methods have primarily focused on modeling local …
and practical applications. Previous methods have primarily focused on modeling local …
FITS: Modeling Time Series with Parameters
In this paper, we introduce FITS, a lightweight yet powerful model for time series analysis.
Unlike existing models that directly process raw time-domain data, FITS operates on the …
Unlike existing models that directly process raw time-domain data, FITS operates on the …
WEITS: A Wavelet-enhanced residual framework for interpretable time series forecasting
Z Guo, Y Sun, T Wu - arXiv preprint arXiv:2405.10877, 2024 - arxiv.org
Time series (TS) forecasting has been an unprecedentedly popular problem in recent years,
with ubiquitous applications in both scientific and business fields. Various approaches have …
with ubiquitous applications in both scientific and business fields. Various approaches have …
MFF-FTNet: Multi-scale Feature Fusion across Frequency and Temporal Domains for Time Series Forecasting
Y Shi, Q Ren, Y Liu, J Sun - arXiv preprint arXiv:2411.17382, 2024 - arxiv.org
Time series forecasting is crucial in many fields, yet current deep learning models struggle
with noise, data sparsity, and capturing complex multi-scale patterns. This paper presents …
with noise, data sparsity, and capturing complex multi-scale patterns. This paper presents …
Rethinking general time series analysis from a frequency domain perspective
Abstract Recently, Transformers and MLPs based models have dominated and made
significant progress in time series analysis. However, these methods struggle to capture the …
significant progress in time series analysis. However, these methods struggle to capture the …
Sequence prediction using spectral RNNs
Fourier methods have a long and proven track record as an excellent tool in data
processing. As memory and computational constraints gain importance in embedded and …
processing. As memory and computational constraints gain importance in embedded and …