M2FMoE: Multi-Resolution Multi-View Frequency Mixture-of-Experts for Extreme-Adaptive Time Series Forecasting

Yaohui Huang; Runmin Zou; Yun Wang; Laeeq Aslam; Ruipeng Dong

AAAI 2026technical0 citations

M2FMoE: Multi-Resolution Multi-View Frequency Mixture-of-Experts for Extreme-Adaptive Time Series Forecasting

Yaohui Huang, Runmin Zou, Yun Wang, Laeeq Aslam, Ruipeng Dong

Abstract

Forecasting time series with extreme events is critical yet challenging due to their high variance, irregular dynamics, and sparse but high-impact nature. While existing methods excel in modeling dominant regular patterns, their performance degrades significantly during extreme events, constituting the primary source of forecasting errors in real-world applications. Although some approaches incorporate auxiliary signals to improve performance, they still fail to capture extreme events

BibTeX

@inproceedings{aaai2026_m2fmoemultiresol,
  title = {M2FMoE: Multi-Resolution Multi-View Frequency Mixture-of-Experts for Extreme-Adaptive Time Series Forecasting},
  author = {Yaohui Huang and Runmin Zou and Yun Wang and Laeeq Aslam and Ruipeng Dong},
  booktitle = {AAAI 2026},
  year = {2026}
}