{"ID":2867742,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17809","arxiv_id":"2509.17809","title":"MTM: A Multi-Scale Token Mixing Transformer for Irregular Multivariate Time Series Classification","abstract":"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.","short_abstract":"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-...","url_abs":"https://arxiv.org/abs/2509.17809","url_pdf":"https://arxiv.org/pdf/2509.17809v1","authors":"[\"Shuhan Zhong\",\"Weipeng Zhuo\",\"Sizhe Song\",\"Guanyao Li\",\"Zhongyi Yu\",\"S. -H. Gary Chan\"]","published":"2025-09-22T14:03:02Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false}