# Wavelet Mixture of Experts for Time Series Forecasting

arXiv: https://arxiv.org/abs/2508.08825 · HTML: https://mlsanity.com/paper/2508.08825/

## Key facts

- Cited by 2 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 22 of its 37 references that are in the map.
- First posted on arXiv 12 Aug 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, 22 of 22)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://mlsanity.com/paper/2106.09305/) (2021)
- [FITS: Modeling Time Series with 10k Parameters](https://mlsanity.com/paper/2307.03756/) (2023)
- [Frequency-domain MLPs are More Effective Learners in Time Series Forecasting](https://mlsanity.com/paper/2311.06184/) (2023)
- [CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting](https://mlsanity.com/paper/2202.01575/) (2022)
- [Go Wider Instead of Deeper](https://mlsanity.com/paper/2107.11817/) (2021)
- [RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series](https://mlsanity.com/paper/1812.01767/) (2018)
- [WFTNet: Exploiting Global and Local Periodicity in Long-term Time Series Forecasting](https://mlsanity.com/paper/2309.11319/) (2023)
- [Temporally Causal Discovery Tests for Discrete Time Series and Neural Spike Trains](https://mlsanity.com/paper/2305.14131/) (2023)
- [Ridge detection for nonstationary multicomponent signals with time-varying wave-shape functions and its applications](https://mlsanity.com/paper/2309.06673/) (2023)
- [Learning Multi-Frequency Partial Correlation Graphs](https://mlsanity.com/paper/2311.15756/) (2023)
- [Information Flow Rate for Cross-Correlated Stochastic Processes](https://mlsanity.com/paper/2401.04950/) (2024)

## Built on by (most cited first, 2 of 2)

- [Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting](https://mlsanity.com/paper/2605.20678/) (2026)
- [CTIA-ODE: Continuous-Time Inter-Variable Attention for Long-Term Time Series Forecasting](https://mlsanity.com/paper/2610.19831/) (2026)

## Abstract (arXiv)

The field of time series forecasting is rapidly advancing, with recent large-scale Transformers and lightweight Multilayer Perceptron (MLP) models showing strong predictive performance. However, conventional Transformer models are often hindered by their large number of parameters and their limited ability to capture non-stationary features in data through smoothing. Similarly, MLP models struggle to manage multi-channel dependencies effectively. To address these limitations, we propose a novel, lightweight time series prediction model, WaveTS-B. This model combines wavelet transforms with MLP to capture both periodic and non-stationary characteristics of data in the wavelet domain. Building on this foundation, we propose a channel clustering strategy that incorporates a Mixture of Experts (MoE) framework, utilizing a gating mechanism and expert network to handle multi-channel dependencies efficiently. We propose WaveTS-M, an advanced model tailored for multi-channel time series prediction. Empirical evaluation across eight real-world time series datasets demonstrates that our WaveTS series models achieve state-of-the-art (SOTA) performance with significantly fewer parameters. Notably, WaveTS-M shows substantial improvements on multi-channel datasets, highlighting its effectiveness.