Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ni, Zhenliang, Ma, Xiaowen, Wu, Zhenkai, Xiao, Shuai, Shu, Han, Chen, Xinghao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914177126236160
author Ni, Zhenliang
Ma, Xiaowen
Wu, Zhenkai
Xiao, Shuai
Shu, Han
Chen, Xinghao
author_facet Ni, Zhenliang
Ma, Xiaowen
Wu, Zhenkai
Xiao, Shuai
Shu, Han
Chen, Xinghao
contents Multivariate time series forecasts are widely used, such as industrial, transportation and financial forecasts. However, the dominant frequencies in time series may shift with the evolving spectral distribution of the data. Traditional Mixture of Experts (MoE) models, which employ a fixed number of experts, struggle to adapt to these changes, resulting in frequency coverage imbalance issue. Specifically, too few experts can lead to the overlooking of critical information, while too many can introduce noise. To this end, we propose Ada-MoGE, an adaptive Gaussian Mixture of Experts model. Ada-MoGE integrates spectral intensity and frequency response to adaptively determine the number of experts, ensuring alignment with the input data's frequency distribution. This approach prevents both information loss due to an insufficient number of experts and noise contamination from an excess of experts. Additionally, to prevent noise introduction from direct band truncation, we employ Gaussian band-pass filtering to smoothly decompose the frequency domain features, further optimizing the feature representation. The experimental results show that our model achieves state-of-the-art performance on six public benchmarks with only 0.2 million parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02061
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series Forecasting
Ni, Zhenliang
Ma, Xiaowen
Wu, Zhenkai
Xiao, Shuai
Shu, Han
Chen, Xinghao
Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
Multivariate time series forecasts are widely used, such as industrial, transportation and financial forecasts. However, the dominant frequencies in time series may shift with the evolving spectral distribution of the data. Traditional Mixture of Experts (MoE) models, which employ a fixed number of experts, struggle to adapt to these changes, resulting in frequency coverage imbalance issue. Specifically, too few experts can lead to the overlooking of critical information, while too many can introduce noise. To this end, we propose Ada-MoGE, an adaptive Gaussian Mixture of Experts model. Ada-MoGE integrates spectral intensity and frequency response to adaptively determine the number of experts, ensuring alignment with the input data's frequency distribution. This approach prevents both information loss due to an insufficient number of experts and noise contamination from an excess of experts. Additionally, to prevent noise introduction from direct band truncation, we employ Gaussian band-pass filtering to smoothly decompose the frequency domain features, further optimizing the feature representation. The experimental results show that our model achieves state-of-the-art performance on six public benchmarks with only 0.2 million parameters.
title Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series Forecasting
topic Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2512.02061