Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Harkati, Aymane, Garouani, Moncef, Teste, Olivier, Aligon, Julien, Hamlich, Mohamed
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.24207
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918408222670848
author Harkati, Aymane
Garouani, Moncef
Teste, Olivier
Aligon, Julien
Hamlich, Mohamed
author_facet Harkati, Aymane
Garouani, Moncef
Teste, Olivier
Aligon, Julien
Hamlich, Mohamed
contents Accurate forecasting of multivariate time series remains challenging due to the need to capture both short-term fluctuations and long-range temporal dependencies. Transformer-based models have emerged as a powerful approach, but their performance depends critically on the representation of temporal data. Traditional point-wise representations preserve individual time-step information, enabling fine-grained modeling, yet they tend to be computationally expensive and less effective at modeling broader contextual dependencies, limiting their scalability to long sequences. Patch-wise representations aggregate consecutive steps into compact tokens to improve efficiency and model local temporal dynamics, but they often discard fine-grained temporal details that are critical for accurate predictions in volatile or complex time series. We propose IPatch, a multi-resolution Transformer architecture that integrates both point-wise and patch-wise tokens, modeling temporal information at multiple resolutions. Experiments on 7 benchmark datasets demonstrate that IPatch consistently improves forecasting accuracy, robustness to noise, and generalization across various prediction horizons compared to single-representation baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24207
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle IPatch: A Multi-Resolution Transformer Architecture for Robust Time-Series Forecasting
Harkati, Aymane
Garouani, Moncef
Teste, Olivier
Aligon, Julien
Hamlich, Mohamed
Machine Learning
Accurate forecasting of multivariate time series remains challenging due to the need to capture both short-term fluctuations and long-range temporal dependencies. Transformer-based models have emerged as a powerful approach, but their performance depends critically on the representation of temporal data. Traditional point-wise representations preserve individual time-step information, enabling fine-grained modeling, yet they tend to be computationally expensive and less effective at modeling broader contextual dependencies, limiting their scalability to long sequences. Patch-wise representations aggregate consecutive steps into compact tokens to improve efficiency and model local temporal dynamics, but they often discard fine-grained temporal details that are critical for accurate predictions in volatile or complex time series. We propose IPatch, a multi-resolution Transformer architecture that integrates both point-wise and patch-wise tokens, modeling temporal information at multiple resolutions. Experiments on 7 benchmark datasets demonstrate that IPatch consistently improves forecasting accuracy, robustness to noise, and generalization across various prediction horizons compared to single-representation baselines.
title IPatch: A Multi-Resolution Transformer Architecture for Robust Time-Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2603.24207