方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| Time-MoE：面向通用时间序列的混合专家模型× | 专家混合模型× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2024 | 2017 |
| 提出者≠ | Xiaoming Shi et al. | Shazeer, N. et al. |
| 类型≠ | Sparse mixture-of-experts autoregressive foundation model | Sparse neural network architecture (conditional computation) |
| 开创性文献≠ | 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 ↗ | Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538 link ↗ |
| 别名≠ | Time Mixture-of-Experts, Time-MoE Foundation Model, Sparse Time-Series Transformer, Zaman Karışık Uzmanlar Modeli | Uzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts |
| 相关 | 3 | 3 |
| 摘要≠ | Time-MoE is a billion-scale autoregressive foundation model for universal time-series forecasting, introduced by Shi et al. in 2024 and accepted at ICLR 2025. It combines a decoder-only transformer architecture with sparse Mixture-of-Experts (MoE) feed-forward layers, enabling the model to scale to billions of parameters while activating only a small subset of expert networks per token—dramatically increasing capacity without proportional compute cost. | Mixture of Experts (MoE) is a sparse neural-network architecture, introduced by Shazeer and colleagues in 2017 with the sparsely-gated MoE layer, in which only a subset of expert sub-networks is activated for each input. As seen in models such as Switch Transformer and Mixtral, it holds computation cost fixed even as the total parameter count grows. |
| ScholarGate数据集 ↗ |
|
|