MTM: A Multi-Scale Token Mixing Transformer for Irregular Multivariate Time Series Classification

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhong, Shuhan, Zhuo, Weipeng, Song, Sizhe, Li, Guanyao, Yu, Zhongyi, Chan, S. -H. Gary
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911168437682176
author Zhong, Shuhan
Zhuo, Weipeng
Song, Sizhe
Li, Guanyao
Yu, Zhongyi
Chan, S. -H. Gary
author_facet Zhong, Shuhan
Zhuo, Weipeng
Song, Sizhe
Li, Guanyao
Yu, Zhongyi
Chan, S. -H. Gary
contents Irregular multivariate time series (IMTS) is characterized by the lack of synchronized observations across its different channels. In this paper, we point out that this channel-wise asynchrony can lead to poor channel-wise modeling of existing deep learning methods. To overcome this limitation, we propose MTM, a multi-scale token mixing transformer for the classification of IMTS. We find that the channel-wise asynchrony can be alleviated by down-sampling the time series to coarser timescales, and propose to incorporate a masked concat pooling in MTM that gradually down-samples IMTS to enhance the channel-wise attention modules. Meanwhile, we propose a novel channel-wise token mixing mechanism which proactively chooses important tokens from one channel and mixes them with other channels, to further boost the channel-wise learning of our model. Through extensive experiments on real-world datasets and comparison with state-of-the-art methods, we demonstrate that MTM consistently achieves the best performance on all the benchmarks, with improvements of up to 3.8% in AUPRC for classification.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17809
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MTM: A Multi-Scale Token Mixing Transformer for Irregular Multivariate Time Series Classification
Zhong, Shuhan
Zhuo, Weipeng
Song, Sizhe
Li, Guanyao
Yu, Zhongyi
Chan, S. -H. Gary
Machine Learning
Irregular multivariate time series (IMTS) is characterized by the lack of synchronized observations across its different channels. In this paper, we point out that this channel-wise asynchrony can lead to poor channel-wise modeling of existing deep learning methods. To overcome this limitation, we propose MTM, a multi-scale token mixing transformer for the classification of IMTS. We find that the channel-wise asynchrony can be alleviated by down-sampling the time series to coarser timescales, and propose to incorporate a masked concat pooling in MTM that gradually down-samples IMTS to enhance the channel-wise attention modules. Meanwhile, we propose a novel channel-wise token mixing mechanism which proactively chooses important tokens from one channel and mixes them with other channels, to further boost the channel-wise learning of our model. Through extensive experiments on real-world datasets and comparison with state-of-the-art methods, we demonstrate that MTM consistently achieves the best performance on all the benchmarks, with improvements of up to 3.8% in AUPRC for classification.
title MTM: A Multi-Scale Token Mixing Transformer for Irregular Multivariate Time Series Classification
topic Machine Learning
url https://arxiv.org/abs/2509.17809