Uporedite metode

	iTransformer	Crossformer	PatchTST
Oblast	Duboko učenje	Duboko učenje	Duboko učenje
Porodica	Machine learning	Machine learning	Machine learning
Godina nastanka	2024	2023	2023
Tvorac	Yong Liu et al.	Yunhao Zhang & Junchi Yan	Nie, Y. et al.
Tip	Inverted-attention sequence model	Transformer-based multivariate time-series forecasting model	Transformer for time series forecasting
Temeljni izvor	Liu, Y., Hu, T., Zhang, H., Wu, H., Wang, S., Ma, L., & Long, M. (2024). iTransformer: Inverted transformers are effective for time series forecasting. ICLR.	Zhang, Y., & Yan, J. (2023). Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. ICLR.	Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR.
Drugi nazivi	Inverted Transformer, iTransformer for Time Series, Inverted Attention Transformer, Ters Transformer	Cross-Dimension Dependency Transformer, Crossformer TSF, Çapraz-Boyut Bağımlılık Transformatörü	PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer
Srodne	2	3	3
Sažetak	iTransformer is a deep-learning architecture for multivariate time-series forecasting introduced by Liu et al. at ICLR 2024. Its defining idea is to invert the conventional Transformer tokenisation strategy: instead of treating each time step as a token, iTransformer treats each variate (sensor channel or feature series) as a single token whose embedding encodes the full observed look-back window. Self-attention is then applied across variates to capture inter-series dependencies, while a feed-forward network within each token learns temporal patterns.	Crossformer is a Transformer-based architecture for multivariate time series forecasting, introduced by Yunhao Zhang and Junchi Yan at ICLR 2023. Unlike earlier Transformer variants that treat each variate independently, Crossformer explicitly models cross-dimension dependencies alongside temporal patterns. It achieves this through a two-stage attention design — cross-time and cross-dimension — applied over segment-level embeddings organized in a hierarchical encoder, enabling the model to capture both intra-variate dynamics and inter-variate correlations simultaneously.	PatchTST is a patch-based Transformer architecture for time series forecasting, introduced by Nie and colleagues in 2023, that cuts each series into overlapping patches treated as tokens and processes channels independently. It balances computational efficiency with strong accuracy on long-horizon forecasting.