Saved in:
Bibliographic Details
Main Authors: Villaboni, Davide, Castellini, Alberto, Danesi, Ivan Luciano, Farinelli, Alessandro
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.17658
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916659607896064
author Villaboni, Davide
Castellini, Alberto
Danesi, Ivan Luciano
Farinelli, Alessandro
author_facet Villaboni, Davide
Castellini, Alberto
Danesi, Ivan Luciano
Farinelli, Alessandro
contents Transformer-based time series forecasting has recently gained strong interest due to the ability of transformers to model sequential data. Most of the state-of-the-art architectures exploit either temporal or inter-channel dependencies, limiting their effectiveness in multivariate time-series forecasting where both types of dependencies are crucial. We propose Sentinel, a full transformer-based architecture composed of an encoder able to extract contextual information from the channel dimension, and a decoder designed to capture causal relations and dependencies across the temporal dimension. Additionally, we introduce a multi-patch attention mechanism, which leverages the patching process to structure the input sequence in a way that can be naturally integrated into the transformer architecture, replacing the multi-head splitting process. Extensive experiments on standard benchmarks demonstrate that Sentinel, because of its ability to "monitor" both the temporal and the inter-channel dimension, achieves better or comparable performance with respect to state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17658
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sentinel: Multi-Patch Transformer with Temporal and Channel Attention for Time Series Forecasting
Villaboni, Davide
Castellini, Alberto
Danesi, Ivan Luciano
Farinelli, Alessandro
Machine Learning
Transformer-based time series forecasting has recently gained strong interest due to the ability of transformers to model sequential data. Most of the state-of-the-art architectures exploit either temporal or inter-channel dependencies, limiting their effectiveness in multivariate time-series forecasting where both types of dependencies are crucial. We propose Sentinel, a full transformer-based architecture composed of an encoder able to extract contextual information from the channel dimension, and a decoder designed to capture causal relations and dependencies across the temporal dimension. Additionally, we introduce a multi-patch attention mechanism, which leverages the patching process to structure the input sequence in a way that can be naturally integrated into the transformer architecture, replacing the multi-head splitting process. Extensive experiments on standard benchmarks demonstrate that Sentinel, because of its ability to "monitor" both the temporal and the inter-channel dimension, achieves better or comparable performance with respect to state-of-the-art approaches.
title Sentinel: Multi-Patch Transformer with Temporal and Channel Attention for Time Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2503.17658