🥰 Some Awesome Time Series Papers for Time Series Analysis.
| Title | Paper | Code |
|---|---|---|
| Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting | [paper] | [code] |
| Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting | [paper] | [code] |
| Pyraformer: Low-complexity Pyramidal Attention for Long-range Time Series Modeling and Forecasting | [paper] | [code] |
| FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting | [paper] | [code] |
| Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting | [paper] | [code] |
| ESTformer: Transformer Utilizing Spatiotemporal Dependencies for Electroencaphalogram Super-resolution | [paper] | [code] |
| Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures | [paper] | [code] |
| FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting | [paper] | [code] |
| Long-term Forecasting with TiDE: Time-series Dense Encoder | [paper] | [code] |
| A Time Series is Worth 64 Words: Long-term Forecasting with Transformers | [paper] | [code] |
| Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting | [paper] | [code] |
| Are Transformers Effective for Time Series Forecasting? | [paper] | [code] |
| TSMixer: An All-MLP Architecture for Time Series Forecasting | [paper] | [code] |
| iTransformer: Inverted Transformers Are Effective for Time Series Forecasting | [paper] | [code] |
| TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting | [paper] | [code] |
| SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention | [paper] | [code] |
| TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables | [paper] | [code] |
| Title | Paper | Code |
|---|---|---|
| TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis | [paper] | [code] |
| One Fits All:Power General Time Series Analysis by Pretrained LM | [paper] | [code] |
| Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis | [paper] | [code] |
| UniTS: A Unified Multi-Task Time Series Model | [paper] | [code] |
| Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation | [paper] | [code] |
| Title | Paper | Code |
|---|---|---|
| One Fits All:Power General Time Series Analysis by Pretrained LM | [paper] | [code] |
| Time-LLM: Time Series Forecasting by Reprogramming Large Language Models | [paper] | [code] |
| S2IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting | [paper] | [code] |
| A decoder-only foundation model for time-series forecasting | [paper] | [code] |
| Title | Paper | Code |
|---|---|---|
| TimeGPT-1 | [paper] | [code] |
| Chronos: Learning the Language of Time Series | [paper] | [code] |
| Unified Training of Universal Time Series Forecasting Transformers | [paper] | [code] |
| Timer: Generative Pre-trained Transformers Are Large Time Series Models | [paper] | [code] |
| MOMENT: A Family of Open Time-series Foundation Models | [paper] | [code] |
| Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts | [paper] | [code] |
| VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters | [paper] | [code] |
| Towards Neural Scaling Laws for Time Series Foundation Models | [paper] | [code] |
| Sundial: A Family of Highly Capable Time Series Foundation Models | [paper] | [code] |