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

• URL: http://arxiv.org/abs/2509.17809v1
• Date: Mon, 22 Sep 2025 14:03:02 GMT
• Title: MTM: A Multi-Scale Token Mixing Transformer for Irregular Multivariate Time Series Classification
• Abstract summary: We propose MTM, a multi-scale token mixing transformer for the classification of IMTS.<n>We find that the channel-wise asynchrony can be alleviated by down-sampling the time series to coarser timescales.<n>We also propose a novel channel-wise token mixing mechanism which proactively chooses important tokens from one channel and mixes them with other channels.
• Score: 9.624687648181231
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Complementarity-Supervised Spectral-Band Routing for Multimodal Emotion Recognition [60.20529806857076]
  Multimodal emotion recognition fuses cues such as text, video, and audio to understand individual emotional states.<n>Prior methods face two main limitations: mechanically relying on independent unimodal performance, and coarse-grained fusion conflicting with the fine-grained representations required by emotion tasks.<n>We propose the Complementarity-Supervised Multi-Band Expert Network, named Atsuko, to model fine-grained complementary features via multi-scale band decomposition and expert collaboration.
  arXiv  Detail & Related papers  (2026-03-07T03:58:48Z)
• HPMixer: Hierarchical Patching for Multivariate Time Series Forecasting [10.068780251829606]
  We propose the Hierarchical Patching Mixer (HPMixer), which models periodicity and residuals in a decoupled yet complementary manner.<n>By integrating decoupled periodicity modeling with structured, multi-scale residual learning, HPMixer provides an effective framework.
  arXiv  Detail & Related papers  (2026-02-18T13:59:04Z)
• Context Video Semantic Transmission with Variable Length and Rate Coding over MIMO Channels [49.624608869195065]
  We propose the context video semantic transmission (CVST) framework for wireless video transmission.<n>We learn a context-channel correlation map to explicitly formulate the relationships between feature groups and multiple input multiple output (MIMO) subchannels.<n>We demonstrate substantial performance gains over various standardized separated coding methods and recent wireless video semantic communication approaches.
  arXiv  Detail & Related papers  (2025-12-23T10:48:43Z)
• Wavelet Mixture of Experts for Time Series Forecasting [7.478995447422547]
  We propose a novel, lightweight time series prediction model, WaveTS-B.<n>This model combines wavelet transforms with a mechanism to capture both periodic and non-stationary characteristics of data in the wavelet domain.<n>We show that our model achieves state-of-the-art (SOTA) performance with significantly fewer parameters.
  arXiv  Detail & Related papers  (2025-08-12T10:32:51Z)
• FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation [57.577843653775]
  We propose textbfFindRec (textbfFlexible unified textbfinformation textbfdisentanglement for multi-modal sequential textbfRecommendation)<n>A Stein kernel-based Integrated Information Coordination Module (IICM) theoretically guarantees distribution consistency between multimodal features and ID streams.<n>A cross-modal expert routing mechanism that adaptively filters and combines multimodal features based on their contextual relevance.
  arXiv  Detail & Related papers  (2025-07-07T04:09:45Z)
• DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting [13.05900224897486]
  Real-world time series often show heterogeneous temporal patterns caused by distribution shifts over time.<n> correlations among channels are complex and intertwined, making it hard to model the interactions among channels precisely and flexibly.<n>We propose a general framework called DUET, which introduces dual clustering on the temporal and channel dimensions.
  arXiv  Detail & Related papers  (2024-12-14T15:15:17Z)
• MTS-UNMixers: Multivariate Time Series Forecasting via Channel-Time Dual Unmixing [3.192685534395382]
  We propose a channel-time dual unmixing network for time series forecasting (named MTS-UNMixer)<n> MTS-UNMixers decomposes the entire series into critical bases and coefficients across both the time and channel dimensions.<n>Results show that MTS-UNMixers significantly outperform existing methods on multiple benchmark datasets.
  arXiv  Detail & Related papers  (2024-11-26T08:23:42Z)
• SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion [59.96233305733875]
  Time series forecasting plays a crucial role in various fields such as finance, traffic management, energy, and healthcare. Several methods utilize mechanisms like attention or mixer to address this by capturing channel correlations. This paper presents an efficient-based model, the Series-cOre Fused Time Series forecaster (SOFTS)
  arXiv  Detail & Related papers  (2024-04-22T14:06:35Z)
• From Similarity to Superiority: Channel Clustering for Time Series Forecasting [61.96777031937871]
  We develop a novel and adaptable Channel Clustering Module ( CCM) CCM dynamically groups channels characterized by intrinsic similarities and leverages cluster information instead of individual channel identities. CCM can boost the performance of CI and CD models by an average margin of 2.4% and 7.2% on long-term and short-term forecasting, respectively.
  arXiv  Detail & Related papers  (2024-03-31T02:46:27Z)
• MCformer: Multivariate Time Series Forecasting with Mixed-Channels Transformer [8.329947472853029]
  Channel Independence (CI) strategy treats all channels as a single channel, expanding the dataset. Mixed Channels strategy combines the data expansion advantages of the CI strategy with the ability to counteract inter-channel correlation forgetting. Model blends a specific number of channels, leveraging an attention mechanism to effectively capture inter-channel correlation information.
  arXiv  Detail & Related papers  (2024-03-14T09:43:07Z)
• SCHEME: Scalable Channel Mixer for Vision Transformers [52.605868919281086]
  Vision Transformers have achieved impressive performance in many computation tasks.<n>We show that the dense connections can be replaced with a sparse block diagonal structure that supports larger expansion ratios.<n>We also propose the use of a lightweight, parameter-free, channel covariance attention mechanism as a parallel branch during training.
  arXiv  Detail & Related papers  (2023-12-01T08:22:34Z)
• A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS [52.51848317549301]
  We propose a Multi-Stage, Multi-Codebook (MSMC) approach to high-performance neural TTS synthesis. A vector-quantized, variational autoencoder (VQ-VAE) based feature analyzer is used to encode Mel spectrograms of speech training data. In synthesis, the neural vocoder converts the predicted MSMCRs into final speech waveforms.
  arXiv  Detail & Related papers  (2022-09-22T09:43:17Z)
• Model-Driven Deep Learning Based Channel Estimation and Feedback for Millimeter-Wave Massive Hybrid MIMO Systems [61.78590389147475]
  This paper proposes a model-driven deep learning (MDDL)-based channel estimation and feedback scheme for millimeter-wave (mmWave) systems. To reduce the uplink pilot overhead for estimating the high-dimensional channels from a limited number of radio frequency (RF) chains, we propose to jointly train the phase shift network and the channel estimator as an auto-encoder. Numerical results show that the proposed MDDL-based channel estimation and feedback scheme outperforms the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-04-22T13:34:53Z)
• Fine Timing and Frequency Synchronization for MIMO-OFDM: An Extreme Learning Approach [8.432859469083951]
  We propose a novel scheme leveraging extreme learning machine (ELM) to achieve high-precision synchronization. The proposed method is robust in terms of the choice of channel parameters and also in terms of "generalization ability" from a machine learning standpoint.
  arXiv  Detail & Related papers  (2020-07-17T21:41:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.