# FreqMoE: Enhancing Time Series Forecasting through Frequency Decomposition Mixture of Experts

arXiv: https://arxiv.org/abs/2501.15125 · HTML: https://mlsanity.com/paper/2501.15125/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts.
- Builds on 1 of its 30 references that are in the map.
- First posted on arXiv 25 Jan 2025.

## Placed in

- Mixture-of-experts / [MoE for time series and graphs](https://mlsanity.com/moe/moe-for-time-series-and-graphs/)

## Builds on (most cited first, 1 of 1)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)

## Built on by (most cited first, 11 of 11)

- [FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decomposition](https://mlsanity.com/paper/2511.11817/) (2025)
- [PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2602.00654/) (2026)
- [Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting](https://mlsanity.com/paper/2509.15105/) (2025)
- [Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Representation Alignment](https://mlsanity.com/paper/2508.07195/) (2025)
- [MoE-Enhanced Multi-Domain Feature Selection and Fusion for Fast Map-Free Trajectory Prediction](https://mlsanity.com/paper/2512.02368/) (2025)
- [M2FMoE: Multi-Resolution Multi-View Frequency Mixture-of-Experts for Extreme-Adaptive Time Series Forecasting](https://mlsanity.com/paper/2601.08631/) (2026)
- [Frequency-aware decomposition learning for sensorless wrench estimation in vibration-rich robotic contact](https://mlsanity.com/paper/2604.12905/) (2026)
- [Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting](https://mlsanity.com/paper/2605.20678/) (2026)
- [FreqLite: A Lightweight Frequency-Decomposed Linear Model with Adaptive Reversible Normalization for Robust Long-Term Time-Series Forecasting](https://mlsanity.com/paper/2606.01339/) (2026)
- [STHMoE: Hypergraph-Enhanced Heterogeneous Dependency Coordination for LLM-Based Urban Traffic Data Forecasting](https://mlsanity.com/paper/2609.15172/) (2026)
- [Disentangling Heterogeneous Traffic Dynamics for Multi-Step Traffic Forecasting via Adaptive Spectral Decomposition](https://mlsanity.com/paper/2609.25777/) (2026)

## Abstract (arXiv)

Long-term time series forecasting is essential in areas like finance and weather prediction. Besides traditional methods that operate in the time domain, many recent models transform time series data into the frequency domain to better capture complex patterns. However, these methods often use filtering techniques to remove certain frequency signals as noise, which may unintentionally discard important information and reduce prediction accuracy. To address this, we propose the Frequency Decomposition Mixture-of-Experts (FreqMoE) model, which dynamically decomposes time series data into frequency bands, each processed by a specialized expert. A gating mechanism adjusts the importance of each output of expert based on frequency characteristics, and the aggregated results are fed into a prediction module that iteratively refines the forecast using residual connections. Our experiments demonstrate that FreqMoE outperforms state-of-the-art models, achieving the best performance on 51 out of 70 metrics across all tested datasets, while significantly reducing the number of required parameters to under 50k, providing notable efficiency advantages. Code is available at: https://github.com/sunbus100/FreqMoE-main