Bandingkan kaedah

	TimeMixer: Pencampuran Multiskala yang Terurai untuk Peramalan Deret Waktu	TimesNet: Pemodelan Variasi Temporal 2D untuk Siri Masa	TSMixer: Seni Bina Semua-MLP untuk Ramalan Deret Masa
Bidang	Pembelajaran Mendalam	Pembelajaran Mendalam	Pembelajaran Mendalam
Keluarga	Machine learning	Machine learning	Machine learning
Tahun asal	2024	2023	2023
Pengasas	Shiyu Wang et al.	Haixu Wu et al.	Si-An Chen et al. (Google)
Jenis	MLP-based multiscale time-series forecasting model	2D convolutional time-series model	All-MLP multivariate time-series forecasting model
Sumber perintis	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.	Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M. (2023). TimesNet: Temporal 2D-variation modeling for general time series analysis. 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.
Alias	Decomposable Multiscale Mixing, Multiscale Time-Series Mixer, TimeMixer Model, Çok Ölçekli Zaman Serisi Karıştırıcı	Temporal 2D-Variation Network, TimesNet Model, 2D Time-Series Network, Zamansal 2B Varyasyon Ağı	All-MLP Time Series Mixer, Time Series Mixer, TSMixer Forecasting Model, Zaman Serisi Karıştırıcı
Berkaitan	3	2	3
Ringkasan	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.	TimesNet is a general-purpose time-series model introduced by Wu et al. at ICLR 2023. Its central idea is that univariate or multivariate time series can be reinterpreted as collections of two-dimensional temporal maps by reshaping the 1D signal according to its dominant periodicities, detected via Fast Fourier Transform. This 1D-to-2D transformation exposes both intraperiod patterns (within one cycle) and interperiod trends (across cycles), enabling powerful 2D convolutional architectures to model temporal variation.	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.