# Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting

arXiv: https://arxiv.org/abs/2402.05956 · HTML: https://mlsanity.com/paper/2402.05956/

## Key facts

- Cited by 104 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 55 references that are in the map.
- First posted on arXiv 4 Feb 2024.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [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)
- [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)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [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)
- [A Multi-Horizon Quantile Recurrent Forecaster](https://mlsanity.com/paper/1711.11053/) (2017)
- [Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting](https://mlsanity.com/paper/1905.03806/) (2019)
- [Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting](https://mlsanity.com/paper/2206.04038/) (2022)
- [AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version](https://mlsanity.com/paper/2112.11174/) (2021)

## Built on by (most cited first, 30 of 104)

- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching](https://mlsanity.com/paper/2410.12261/) (2024)
- [Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification](https://mlsanity.com/paper/2405.19363/) (2024)
- [Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective](https://mlsanity.com/paper/2510.14510/) (2025)
- [Patch-wise Structural Loss for Time Series Forecasting](https://mlsanity.com/paper/2503.00877/) (2025)
- [Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer](https://mlsanity.com/paper/2405.17478/) (2024)
- [LightGTS: A Lightweight General Time Series Forecasting Model](https://mlsanity.com/paper/2506.06005/) (2025)
- [Aurora: Towards Universal Generative Multimodal Time Series Forecasting](https://mlsanity.com/paper/2509.22295/) (2025)
- [Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems](https://mlsanity.com/paper/2410.19892/) (2024)
- [HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series](https://mlsanity.com/paper/2510.25785/) (2025)
- [CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling](https://mlsanity.com/paper/2510.12489/) (2025)
- [Time-SSM: Simplifying and Unifying State Space Models for Time Series Forecasting](https://mlsanity.com/paper/2405.16312/) (2024)
- [AttenGluco: Multimodal Transformer-Based Blood Glucose Forecasting on AI-READI Dataset](https://mlsanity.com/paper/2502.09919/) (2025)
- [Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models](https://mlsanity.com/paper/2509.25826/) (2025)
- [ms-Mamba: Multi-scale Mamba for Time-Series Forecasting](https://mlsanity.com/paper/2504.07654/) (2025)
- [Orca: Ocean Significant Wave Height Estimation with Spatio-temporally Aware Large Language Models](https://mlsanity.com/paper/2407.20053/) (2024)
- [Are KANs Effective for Multivariate Time Series Forecasting?](https://mlsanity.com/paper/2408.11306/) (2024)
- [Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow Matching](https://mlsanity.com/paper/2507.07192/) (2025)
- [Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecasting](https://mlsanity.com/paper/2603.15452/) (2026)
- [Interpretability for Time Series Transformers using A Concept Bottleneck Framework](https://mlsanity.com/paper/2410.06070/) (2024)
- [Unveiling the Potential of Text in High-Dimensional Time Series Forecasting](https://mlsanity.com/paper/2501.07048/) (2025)
- [Using Causality for Enhanced Prediction of Web Traffic Time Series](https://mlsanity.com/paper/2502.00612/) (2025)
- [TimeFound: A Foundation Model for Time Series Forecasting](https://mlsanity.com/paper/2503.04118/) (2025)
- [MSGM: A Multi-Scale Spatiotemporal Graph Mamba for EEG Emotion Recognition](https://mlsanity.com/paper/2507.15914/) (2025)
- [SC-JEPA: Stabilizing Latent Predictive Learning for Time-Series Anomaly Prediction](https://mlsanity.com/paper/2602.04643/) (2026)
- [Baguan-TS: A Sequence-Native In-Context Learning Model for Time Series Forecasting with Covariates](https://mlsanity.com/paper/2603.17439/) (2026)
- [Towards Lightweight Time Series Forecasting: a Patch-wise Transformer with Weak Data Enriching](https://mlsanity.com/paper/2501.10448/) (2025)
- [MSDformer: Multi-scale Discrete Transformer For Time Series Generation](https://mlsanity.com/paper/2505.14202/) (2025)
- [Why Attention Fails: The Degeneration of Transformers into MLPs in Time Series Forecasting](https://mlsanity.com/paper/2509.20942/) (2025)
- [FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting](https://mlsanity.com/paper/2512.14253/) (2025)

## Abstract (arXiv)

Transformers for time series forecasting mainly model time series from limited or fixed scales, making it challenging to capture different characteristics spanning various scales. We propose Pathformer, a multi-scale Transformer with adaptive pathways. It integrates both temporal resolution and temporal distance for multi-scale modeling. Multi-scale division divides the time series into different temporal resolutions using patches of various sizes. Based on the division of each scale, dual attention is performed over these patches to capture global correlations and local details as temporal dependencies. We further enrich the multi-scale Transformer with adaptive pathways, which adaptively adjust the multi-scale modeling process based on the varying temporal dynamics of the input, improving the accuracy and generalization of Pathformer. Extensive experiments on eleven real-world datasets demonstrate that Pathformer not only achieves state-of-the-art performance by surpassing all current models but also exhibits stronger generalization abilities under various transfer scenarios. The code is made available at https://github.com/decisionintelligence/pathformer.