TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
By Haixu Wu, Teng Hu, Yong Liu, Hang Zhou, Jianmin Wang, Mingsheng Long. International Conference on Learning Representations, 2022
2,354 citations recorded by the source corpus.
Time series analysis is of immense importance in extensive applications, such as weather forecasting, anomaly detection, and action recognition. This paper focuses on temporal variation modeling, which is the common key problem of extensive analysis tasks. Previous methods attempt to accomplish this directly from the 1D time series, which is extremely challenging due to the intricate temporal patterns. Based on the observation of multi-periodicity in time series, we ravel out the complex temporal variations into the multiple intraperiod- and interperiod-variations. To tackle the limitations of 1D time series in representation capability, we extend the analysis of temporal variations into the 2D space by transforming the 1D time series into a set of 2D tensors based on multiple periods. This transformation can embed the intraperiod- and interperiod-variations into the columns and rows of the 2D tensors respectively, making the 2D-variations to be easily modeled by 2D kernels. Technically, we propose the TimesNet with TimesBlock as a task-general backbone for time series analysis. TimesBlock can discover the multi-periodicity adaptively and extract the complex temporal variations from transformed 2D tensors by a parameter-efficient inception block. Our proposed TimesNet achieves consistent state-of-the-art in five mainstream time series analysis tasks, including short- and long-term forecasting, imputation, classification, and anomaly detection. Code is available at this repository: https://github.com/thuml/TimesNet.
Subfields: Artificial Intelligence, Transportation, Signal Processing
View Paper: https://www.semanticscholar.org/paper/47696145b3f88c4cc3f3c22035286b5d7ebce09d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Silvio Savarese
- Mingsheng Long
- Caiming Xiong
- Doyen Sahoo
- Mohit Bansal
- Chenghao Liu
- Sergey Levine
- Donghao Luo
In Transportation
In Signal Processing
Citations in the corpus
- Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts (2024, neutral): “M O E up to 2.4 billion parameters with around 1 billion of them activated.”
- MOMENT: A Family of Open Time-series Foundation Models (2024, methodology): “We would like to emphasize that all datasets used in this study are publicly available.”
- ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis (2024, methodology): “Setups For classification, we select 10 multivariate datasets from UEA Time Series Classification Archive (Bagnall et al., 2018) for benchmarking and pre-process the datasets following (Wu et al., 2023).”
- iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (2023, methodology): “…al., 2021), FEDformer (Zhou et al., 2022), Stationary (Liu et al., 2022b), Crossformer (Zhang & Yan, 2023), PatchTST (Nie et al., 2023); (2) Linear-based methods: DLinear (Zeng et al., 2023), TiDE (Das et al., 2023); and (3) TCN-based methods: SCINet (Liu et al., 2022a), TimesNet (Wu et al., 2023).”
- TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting (2024, methodology): “…capture temporal variations with well-designed architectures, which span a wide range of foundation backbones, including CNN (Wang et al., 2023; Wu et al., 2023a; Hewage et al., 2020), RNN (Lai et al., 2018; Qin et al., 2017; Salinas et al., 2020), Transformer (Vaswani et al., 2017; Zhou et…”
- Unified Training of Universal Time Series Forecasting Transformers (2024, methodology): “Zhou et al. (2023); Jin et al. (2023) introduce modules and fine-tuning methods to adapt LLMs for time series tasks including forecasting.”
- Time-LLM: Time Series Forecasting by Reprogramming Large Language Models (2023, methodology): “To ensure a fair comparison, we adhere to the experimental configurations in (Wu et al., 2022) across all baselines with a unified evaluation pipeline 1 .”
- FITS: Modeling Time Series with 10k Parameters (2023, methodology): “Following TimesNet (Wu et al., 2023), we also compare the anomaly detection performance with other models (Zeng et al., 2023; Zhang et al., 2022; Woo et al., 2022; Zhou et al., 2022a).”
- One Fits All: Power General Time Series Analysis by Pretrained LM (2023, methodology): “To ensure a fair comparison, we use GPT2-backbone FPT and adhere to the experimental settings of TimesNet Wu et al. (2023).”
- TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval (2025, unknown): “Formally, the channel-level negative set is defined as: and similarly in the reverse direction:”