Methoden vergleichen

	Time-MoE: Ein Foundation Model für Zeitreihen basierend auf Mixture-of-Experts	Mixture of Experts	TimesFM: Ein Decoder-Only Foundation Model für Zeitreihenprognosen
Fachgebiet	Deep Learning	Deep Learning	Deep Learning
Familie	Machine learning	Machine learning	Machine learning
Entstehungsjahr	2024	2017	2024
Urheber	Xiaoming Shi et al.	Shazeer, N. et al.	Abhimanyu Das et al. (Google)
Typ	Sparse mixture-of-experts autoregressive foundation model	Sparse neural network architecture (conditional computation)	Pre-trained decoder-only transformer for zero-shot time-series forecasting
Wegweisende Quelle	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.	Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538	Das, A., Kong, W., Sen, R., & Zhou, Y. (2024). A decoder-only foundation model for time-series forecasting. ICML.
Aliasnamen	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	Time-series Foundation Model, Google TimesFM, TimesFM forecaster, Zaman Serisi Temel Modeli
Verwandt	3	3	3
Zusammenfassung	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.	TimesFM is a pre-trained foundation model for univariate time-series forecasting introduced by Abhimanyu Das, Weihao Kong, Rajat Sen, and Yichen Zhou from Google in 2024. The model adopts a decoder-only transformer architecture, similar in spirit to large language models, and is trained on a large corpus of real-world and synthetic time-series data. Its central innovation is the ability to perform accurate zero-shot forecasting across diverse domains without task-specific fine-tuning.