# MoE for time series and graphs

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

## Key facts

- MoE for time series and graphs: 114 papers on arXiv since 2019 (data through 14 Oct 2026).
- 18 of its 114 mapped papers (16%) cite “Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts” (2024, arXiv 2409.16040).
- 12 of its 114 mapped papers (11%) cite “Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts” (2024, arXiv 2410.10469).
- 3 new papers 17 Sep–14 Oct.

## Most cited here

- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024), cited by 18 papers here
- [Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts](https://mlsanity.com/paper/2410.10469/) (2024), cited by 12 papers here
- [Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling](https://mlsanity.com/paper/2304.02806/) (2023), cited by 6 papers here
- [Spatial Mixture-of-Experts](https://mlsanity.com/paper/2211.13491/) (2022), cited by 4 papers here
- [TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts](https://mlsanity.com/paper/2403.02600/) (2024), cited by 3 papers here
- [GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts](https://mlsanity.com/paper/2312.04693/) (2023), cited by 2 papers here
- [Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach](https://mlsanity.com/paper/2406.03464/) (2024), cited by 2 papers here
- [Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction](https://mlsanity.com/paper/2406.12923/) (2024), cited by 2 papers here
- [Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2412.19108/) (2024), cited by 2 papers here
- [FreqMoE: Enhancing Time Series Forecasting through Frequency Decomposition Mixture of Experts](https://mlsanity.com/paper/2501.15125/) (2025), cited by 2 papers here

## New (17 Sep–14 Oct)

- [Beyond Static Positional Encoding: Bayesian Time-aware Attention for Non-Stationary Long-term Time Series Forecasting](https://mlsanity.com/paper/2610.19603/) (2026-10-14)
- [Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation Models](https://mlsanity.com/paper/2609.39445/) (2026-09-30)
- [OceanMoE: Structured Conditional Sparse Computation for Long-Horizon Multivariate Ocean Forecasting](https://mlsanity.com/paper/2609.19768/) (2026-09-17)