# PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting

arXiv: https://arxiv.org/abs/2310.00655 · HTML: https://mlsanity.com/paper/2310.00655/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 1 Oct 2023.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (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)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [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)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Hyena Hierarchy: Towards Larger Convolutional Language Models](https://mlsanity.com/paper/2302.10866/) (2023)
- [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://mlsanity.com/paper/2106.09305/) (2021)
- [Long-term Forecasting with TiDE: Time-series Dense Encoder](https://mlsanity.com/paper/2304.08424/) (2023)
- [Patches Are All You Need?](https://mlsanity.com/paper/2201.09792/) (2022)
- [CKConv: Continuous Kernel Convolution For Sequential Data](https://mlsanity.com/paper/2102.02611/) (2021)
- [MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing](https://mlsanity.com/paper/2302.04501/) (2023)
- [Rigid-Motion Scattering for Texture Classification](https://mlsanity.com/paper/1403.1687/) (2014)
- [PETformer: Long-term Time Series Forecasting via Placeholder-enhanced Transformer](https://mlsanity.com/paper/2308.04791/) (2023)

## Built on by (most cited first, 20 of 20)

- [CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns](https://mlsanity.com/paper/2409.18479/) (2024)
- [PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection](https://mlsanity.com/paper/2401.09793/) (2024)
- [Conditional Denoising Meets Polynomial Modeling: A Flexible Decoupled Framework for Time Series Forecasting](https://mlsanity.com/paper/2410.13253/) (2024)
- [KANMixer: a minimal KAN-centered mixer for long-term time series forecasting](https://mlsanity.com/paper/2508.01575/) (2025)
- [A New Perspective on Time Series Anomaly Detection: Faster Patch-based Broad Learning System](https://mlsanity.com/paper/2412.05498/) (2024)
- [ModelRadar: Aspect-based Forecast Evaluation](https://mlsanity.com/paper/2504.00059/) (2025)
- [MFRS: A Multi-Frequency Reference Series Approach to Scalable and Accurate Time-Series Forecasting](https://mlsanity.com/paper/2503.08328/) (2025)
- [TriP-LLM: A Tri-Branch Patch-wise Large Language Model Framework for Time-Series Anomaly Detection](https://mlsanity.com/paper/2508.00047/) (2025)
- [TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting](https://mlsanity.com/paper/2512.22550/) (2025)
- [PMDformer: Patch-Mean Decoupling Information Transformer for Long-term Forecasting](https://mlsanity.com/paper/2606.26549/) (2026)
- [IIP-Mixer:Intra-Inter Patch Mixing Architecture for Battery Remaining Useful Life Prediction](https://mlsanity.com/paper/2403.18379/) (2024)
- [Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecasting](https://mlsanity.com/paper/2505.11017/) (2025)
- [JustDense: Just using Dense instead of Sequence Mixer for Time Series analysis](https://mlsanity.com/paper/2508.09153/) (2025)
- [Echo Flow Networks](https://mlsanity.com/paper/2509.24122/) (2025)
- [Naga: Vedic Encoding for Deep State Space Models](https://mlsanity.com/paper/2511.13510/) (2025)
- [DB2-TransF: All You Need Is Learnable Daubechies Wavelets for Time Series Forecasting](https://mlsanity.com/paper/2512.10051/) (2025)
- [ITS-Mina: A Harris Hawks Optimization-Based All-MLP Framework with Iterative Refinement and External Attention for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2604.27981/) (2026)
- [QuITE: Query-Based Irregular Time Series Embedding](https://mlsanity.com/paper/2605.28166/) (2026)
- [Challenges of Explainability in Continual Learning for Time Series Forecasting](https://mlsanity.com/paper/2607.19382/) (2026)
- [Attention-based Experience Replay Framework for Continual Learning of Agnostic Time Series Forecasting Models](https://mlsanity.com/paper/2607.20493/) (2026)

## Abstract (arXiv)

Although the Transformer has been the dominant architecture for time series forecasting tasks in recent years, a fundamental challenge remains: the permutation-invariant self-attention mechanism within Transformers leads to a loss of temporal information. To tackle these challenges, we propose PatchMixer, a novel CNN-based model. It introduces a permutation-variant convolutional structure to preserve temporal information. Diverging from conventional CNNs in this field, which often employ multiple scales or numerous branches, our method relies exclusively on depthwise separable convolutions. This allows us to extract both local features and global correlations using a single-scale architecture. Furthermore, we employ dual forecasting heads encompassing linear and nonlinear components to better model future curve trends and details. Our experimental results on seven time-series forecasting benchmarks indicate that compared with the state-of-the-art method and the best-performing CNN, PatchMixer yields 3.9% and 21.2% relative improvements, respectively, while being 2-3x faster than the most advanced method.