# Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration

arXiv: https://arxiv.org/abs/2605.10330 · HTML: https://mlsanity.com/paper/2605.10330/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts.
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 11 May 2026.

## 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, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [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)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [BASE Layers: Simplifying Training of Large, Sparse Models](https://mlsanity.com/paper/2103.16716/) (2021)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [Monash Time Series Forecasting Archive](https://mlsanity.com/paper/2105.06643/) (2021)
- [Conditional Time Series Forecasting with Convolutional Neural Networks](https://mlsanity.com/paper/1703.04691/) (2017)
- [Taming Sparsely Activated Transformer with Stochastic Experts](https://mlsanity.com/paper/2110.04260/) (2021)
- [Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts](https://mlsanity.com/paper/2410.10469/) (2024)
- [Mixture-of-Linear-Experts for Long-term Time Series Forecasting](https://mlsanity.com/paper/2312.06786/) (2023)
- [LeMoLE: LLM-Enhanced Mixture of Linear Experts for Time Series Forecasting](https://mlsanity.com/paper/2412.00053/) (2024)
- [Electricity Price Forecasting: Bridging Linear Models, Neural Networks and Online Learning](https://mlsanity.com/paper/2601.02856/) (2026)

## Abstract (arXiv)

We propose a novel Mixture-of-Experts framework, referred to as Expert Loss Integration MoE (EliMoE), for time series forecasting. EliMoE addresses the optimization problem arising from small gating weights by incorporating expert-specific losses, which provide each expert with a direct learning signal independent of the gate-assigned weight. Specifically, the overall objective comprises the base forecasting loss and expert-specific losses, allowing individual expert prediction errors to directly influence parameter updates alongside the aggregate forecasting error. The framework also encourages different experts to learn from different temporal segments of the data. The proposed framework is further combined with a partial online learning strategy that enables efficient incremental updates of model parameters. By integrating expert-level loss information with partial online learning, EliMoE improves forecasting performance while retaining computational efficiency. Empirical results across five benchmark datasets from diverse application domains with different sampling frequencies show that the proposed approach generally outperforms state-of-the-art supervised neural forecasting models, including Transformer-based architectures such as PatchTST, as well as zero-shot time-series foundation models such as TimeMoE. Furthermore, ablation studies confirm the effectiveness of the expert-specific loss integration strategy, highlighting its contribution to enhancing predictive performance.