مقایسهٔ روش‌ها

	TimeMixer: ترکیبی چندمقیاسی تجزیه‌پذیر برای پیش‌بینی سری‌های زمانی	TSMixer: معماری تمام MLP برای پیش‌بینی سری زمانی
حوزه	یادگیری عمیق	یادگیری عمیق
خانواده	Machine learning	Machine learning
سال پیدایش	2024	2023
پدیدآور	Shiyu Wang et al.	Si-An Chen et al. (Google)
نوع	MLP-based multiscale time-series forecasting model	All-MLP multivariate time-series forecasting model
منبع بنیادین	Wang, S., Wu, H., Shi, X., Hu, T., Luo, H., Ma, L., Zhang, J. Y., & Zhou, J. (2024). TimeMixer: Decomposable multiscale mixing for time series forecasting. ICLR.	Chen, S.-A., Li, C.-L., Yoder, N., Arik, S. O., & Pfister, T. (2023). TSMixer: An all-MLP architecture for time series forecasting. Transactions on Machine Learning Research.
نام‌های دیگر	Decomposable Multiscale Mixing, Multiscale Time-Series Mixer, TimeMixer Model, Çok Ölçekli Zaman Serisi Karıştırıcı	All-MLP Time Series Mixer, Time Series Mixer, TSMixer Forecasting Model, Zaman Serisi Karıştırıcı
مرتبط	3	3
خلاصه	TimeMixer is a decomposition-based, attention-free time-series forecasting architecture introduced by Wang et al. at ICLR 2024. The central idea is to disentangle seasonal and trend components across multiple temporal scales constructed by average pooling, then mix information across those scales using lightweight MLP blocks. By handling coarse (trend-dominant) and fine (seasonal-dominant) resolutions separately and combining their predictions, TimeMixer avoids the quadratic cost of attention while capturing both local and global temporal patterns.	TSMixer is a multivariate time-series forecasting model introduced by Si-An Chen and colleagues at Google in 2023. It challenges the prevailing dominance of Transformer-based architectures by demonstrating that a simple stack of interleaved MLP layers — alternating between mixing along the time axis and mixing across feature channels — achieves strong forecasting accuracy while remaining computationally efficient and easy to interpret architecturally.