# MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing

arXiv: https://arxiv.org/abs/2302.04501 · HTML: https://mlsanity.com/paper/2302.04501/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 9 Feb 2023.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [FNet: Mixing Tokens with Fourier Transforms](https://mlsanity.com/paper/2105.03824/) (2021)
- [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://mlsanity.com/paper/2106.09305/) (2021)
- [Synthesizer: Rethinking Self-Attention in Transformer Models](https://mlsanity.com/paper/2005.00743/) (2020)
- [ETSformer: Exponential Smoothing Transformers for Time-series Forecasting](https://mlsanity.com/paper/2202.01381/) (2022)
- [N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting](https://mlsanity.com/paper/2201.12886/) (2022)
- [Attend and Diagnose: Clinical Time Series Analysis using Attention Models](https://mlsanity.com/paper/1711.03905/) (2017)
- [Is Attention Better Than Matrix Decomposition?](https://mlsanity.com/paper/2109.04553/) (2021)
- [Reflash Dropout in Image Super-Resolution](https://mlsanity.com/paper/2112.12089/) (2021)
- [MetaFormer: A Unified Meta Framework for Fine-Grained Recognition](https://mlsanity.com/paper/2203.02751/) (2022)
- [CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputation](https://mlsanity.com/paper/1905.09904/) (2019)

## Built on by (most cited first, 30 of 53)

- [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://mlsanity.com/paper/2405.14616/) (2024)
- [TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis](https://mlsanity.com/paper/2410.16032/) (2024)
- [CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns](https://mlsanity.com/paper/2409.18479/) (2024)
- [CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting](https://mlsanity.com/paper/2305.12095/) (2023)
- [SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting](https://mlsanity.com/paper/2308.11200/) (2023)
- [From Similarity to Superiority: Channel Clustering for Time Series Forecasting](https://mlsanity.com/paper/2404.01340/) (2024)
- [Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting](https://mlsanity.com/paper/2406.03751/) (2024)
- [A Survey of Deep Learning and Foundation Models for Time Series Forecasting](https://mlsanity.com/paper/2401.13912/) (2024)
- [Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators](https://mlsanity.com/paper/2401.17548/) (2024)
- [Temporal Query Network for Efficient Multivariate Time Series Forecasting](https://mlsanity.com/paper/2505.12917/) (2025)
- [PETformer: Long-term Time Series Forecasting via Placeholder-enhanced Transformer](https://mlsanity.com/paper/2308.04791/) (2023)
- [RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks](https://mlsanity.com/paper/2401.09093/) (2024)
- [MotionTrack: Learning Motion Predictor for Multiple Object Tracking](https://mlsanity.com/paper/2306.02585/) (2023)
- [PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting](https://mlsanity.com/paper/2310.00655/) (2023)
- [MultiSPANS: A Multi-range Spatial-Temporal Transformer Network for Traffic Forecast via Structural Entropy Optimization](https://mlsanity.com/paper/2311.02880/) (2023)
- [TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning](https://mlsanity.com/paper/2405.03140/) (2024)
- [Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping](https://mlsanity.com/paper/2305.10721/) (2023)
- [SageFormer: Series-Aware Framework for Long-term Multivariate Time Series Forecasting](https://mlsanity.com/paper/2307.01616/) (2023)
- [MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification](https://mlsanity.com/paper/2503.05582/) (2025)
- [A Mamba Foundation Model for Time Series Forecasting](https://mlsanity.com/paper/2411.02941/) (2024)
- [TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation](https://mlsanity.com/paper/2503.07674/) (2025)
- [On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecasting](https://mlsanity.com/paper/2408.09695/) (2024)
- [A Joint Time-frequency Domain Transformer for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2305.14649/) (2023)
- [MambaSL: Exploring Single-Layer Mamba for Time Series Classification](https://mlsanity.com/paper/2604.15174/) (2026)
- [LiNo: Advancing Recursive Residual Decomposition of Linear and Nonlinear Patterns for Robust Time Series Forecasting](https://mlsanity.com/paper/2410.17159/) (2024)
- [TFKAN: Time-Frequency KAN for Long-Term Time Series Forecasting](https://mlsanity.com/paper/2506.12696/) (2025)
- [Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning](https://mlsanity.com/paper/2401.17802/) (2024)
- [Two-Stage Aggregation with Dynamic Local Attention for Irregular Time Series](https://mlsanity.com/paper/2311.07744/) (2023)
- [TiVaT: A Transformer with a Single Unified Mechanism for Capturing Asynchronous Dependencies in Multivariate Time Series Forecasting](https://mlsanity.com/paper/2410.01531/) (2024)
- [EffiCANet: Efficient Time Series Forecasting with Convolutional Attention](https://mlsanity.com/paper/2411.04669/) (2024)

## Abstract (arXiv)

Multivariate time series forecasting has been widely used in various practical scenarios. Recently, Transformer-based models have shown significant potential in forecasting tasks due to the capture of long-range dependencies. However, recent studies in the vision and NLP fields show that the role of attention modules is not clear, which can be replaced by other token aggregation operations. This paper investigates the contributions and deficiencies of attention mechanisms on the performance of time series forecasting. Specifically, we find that (1) attention is not necessary for capturing temporal dependencies, (2) the entanglement and redundancy in the capture of temporal and channel interaction affect the forecasting performance, and (3) it is important to model the mapping between the input and the prediction sequence. To this end, we propose MTS-Mixers, which use two factorized modules to capture temporal and channel dependencies. Experimental results on several real-world datasets show that MTS-Mixers outperform existing Transformer-based models with higher efficiency.