Сравнение методов
Просматривайте выбранные методы рядом; строки с различиями подсвечены.
| TimeMixer× | DLinear× | TimesNet: Моделирование временных двумерных вариаций для временных рядов× | |
|---|---|---|---|
| Область | Глубокое обучение | Глубокое обучение | Глубокое обучение |
| Семейство | Machine learning | Machine learning | Machine learning |
| Год появления≠ | 2024 | 2023 | 2023 |
| Автор метода≠ | Shiyu Wang et al. | Ailing Zeng et al. | Haixu Wu et al. |
| Тип≠ | MLP-based multiscale time-series forecasting model | Decomposition-based linear forecasting model | 2D convolutional time-series model |
| Основополагающий источник≠ | 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. link ↗ | Zeng, A., Chen, M., Zhang, L., & Xu, Q. (2023). Are transformers effective for time series forecasting? AAAI. link ↗ | Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M. (2023). TimesNet: Temporal 2D-variation modeling for general time series analysis. ICLR. link ↗ |
| Другие названия | Decomposable Multiscale Mixing, Multiscale Time-Series Mixer, TimeMixer Model, Çok Ölçekli Zaman Serisi Karıştırıcı | Decomposition Linear, DLinear Forecaster, Linear Decomposition Model, Ayrışım Doğrusal Modeli | Temporal 2D-Variation Network, TimesNet Model, 2D Time-Series Network, Zamansal 2B Varyasyon Ağı |
| Связанные≠ | 3 | 3 | 2 |
| Сводка≠ | 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. | DLinear is a lightweight time series forecasting model introduced by Zeng et al. at AAAI 2023. It challenges the prevailing assumption that Transformer-based architectures are necessary for accurate long-horizon forecasting. The model decomposes an input sequence into trend and seasonal components using a moving average filter, then applies separate single-layer linear transformations to each component before summing their outputs to produce the final forecast. | 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. |
| ScholarGateНабор данных ↗ |
|
|
|