Pith. sign in

REVIEW 11 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.05956 v5 pith:MM2JDNGJ submitted 2024-02-04 cs.LG

Peng Chen , Yingying Zhang , Yunyao Cheng , Yang Shu , Yihang Wang , Qingsong Wen , Bin Yang , Chenjuan Guo This is my paper · ORCID
classification cs.LG
keywords multi-scalepathformertemporalseriestimeadaptivepathwaysvarious
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 36 citations worldwide. Full citation record

  1. Regime-Aware Physics-Guided Early Warning of Lithium-Ion Battery Thermal Runaway Using Thermo-Mechanical Signals

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A regime-gated TCN with SOC-FiLM conditioning fuses thermo-mechanical signals to warn of battery thermal runaway 15.6 s before onset on 30 mechanical-abuse tests, with force the most important channel.

  2. Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting

    cs.AI 2026-06 conditional novelty 6.0 of 10

    DiffDiff rewires diffusion forecasting so corruption gradually emphasizes second-order differences, concentrating generation on history-uncertain parts and improving forecasts on seven benchmarks.

  3. The Power of Architecture: Deep Dive into Transformer Architectures for Long-Term Time Series Forecasting

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Bidirectional joint-attention, complete forecasting aggregation, and direct mapping form the most effective Transformer design for long-term time series forecasting.

  4. Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Using Fourier basis expansion to build time-frequency features improves long-term and short-term time series forecasting across linear, MLP, and transformer backbones.

  5. DisMS-TS: Eliminating Redundant Multi-Scale Features for Time Series Classification

    cs.AI 2025-07 conditional novelty 5.0 of 10

    A multi-scale time series classifier that disentangles scale-shared and scale-specific features and reports improved accuracy on six benchmarks.

  6. PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A physics-informed positional encoding that embeds timestamps and latitude/longitude into a vision language model improves typhoon intensity and track forecasting on the Digital Typhoon dataset.

  7. SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting

    cs.LG 2026-02 conditional novelty 4.0 of 10

    SEMixer combines random-mask patch interactions with progressive adjacent-scale mixing and reports improved MSE/MAE on common long-term forecasting benchmarks.

  8. Towards Measuring and Modeling Geometric Structures in Time Series Forecasting via Image Modality

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A new image-based similarity metric (TGSI) and a three-part training loss (SATL) that together aim to improve the geometric fidelity of time series forecasts.

  9. Foundation Models for Demand Forecasting via Dual-Strategy Ensembling

    cs.LG 2025-07 conditional novelty 4.0 of 10

    A dual ensemble of hierarchical partitions and diverse backbones improves foundation-model sales forecasts on M5 and three external datasets, though the zero-shot protocol is under-specified.

  10. MSGM: A Multi-Scale Spatiotemporal Graph Mamba for EEG Emotion Recognition

    eess.SP 2025-07 conditional novelty 4.0 of 10

    MSGM, a graph-Mamba model with multi-scale temporal segmentation and global-local graphs, reports state-of-the-art subject-independent EEG emotion classification on SEED, THU-EP, and FACED.

  11. AttenGluco: Multimodal Transformer-Based Blood Glucose Forecasting on AI-READI Dataset

    cs.LG 2025-02 conditional novelty 4.0 of 10

    A multimodal Transformer with cross-attention and multi-scale attention forecasts blood glucose from CGM and activity data, beating a CNN-LSTM baseline on AI-READI by about 10% in RMSE.

Pith tools