Machine learningTime-series forecasting
Time-MoE：面向通用时间序列的混合专家模型
Time-MoE是由Shi等人于2024年提出、并被ICLR 2025接收的、面向通用时间序列预测的十亿级自回归基础模型。它结合了仅解码器Transformer架构和稀疏混合专家（MoE）前馈层，使得模型能够扩展到数十亿参数，同时每个token仅激活一小部分专家网络——在不按比例增加计算成本的情况下大幅提升模型容量。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Shi, X., Wang, S., Nie, Y., Li, D., Ye, Z., Wen, Q., & Jin, M. (2024). Time-MoE: Billion-scale time series foundation models with mixture of experts. ICLR 2025. link ↗
如何引用本页
ScholarGate. (2026, June 2). Time-MoE (Mixture-of-Experts Time-Series Foundation Model). ScholarGate. https://scholargate.app/zh/deep-learning/time-moe
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →