MSMixer: Learned Multi-Scale Temporal Mixing with Complementary Linear Shortcut for Long-Term Time Series Forecasting

• URL: http://arxiv.org/abs/2605.02689v1
• Date: Mon, 04 May 2026 15:03:46 GMT
• Title: MSMixer: Learned Multi-Scale Temporal Mixing with Complementary Linear Shortcut for Long-Term Time Series Forecasting
• Abstract summary: Long-term time series forecasting requires models that simultaneously capture rapid oscillations, medium-range periodicities, and slowly evolving macro-trends from a fixed look-back window.<n>Existing lightweight-based models typically operate on a single temporal resolution, limiting their ability to explicitly model patterns at multiple scales.<n>We propose MSMixer, a channel-independent multi-scale architecture that addresses this limitation through three complementary innovations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-term time series forecasting requires models that simultaneously capture rapid oscillations, medium-range periodicities, and slowly evolving macro-trends from a fixed look-back window. Existing lightweight MLP-based models typically operate on a single temporal resolution, limiting their ability to explicitly model patterns at multiple scales. We propose MSMixer, a channel-independent multi-scale MLP architecture that addresses this limitation through three complementary innovations: (i) three parallel scale branches at down-sample factors {1x, 4x, 16x} with independent MLP blocks, (ii) a learnable softmax gate that dynamically weighs branch outputs, and (iii) a DLinear complementary shortcut that provides full-window trend and seasonality context. MSMixer contains only 112K parameters at H=96 and runs at O(T) complexity. Evaluated on four ETT benchmarks with standard chronological splits and three random seeds, MSMixer achieves the lowest average MSE (0.357) among lightweight models, outperforming DLinear (0.386, -7.4%) and NLinear (0.365, -2.1%), winning 12 of 16 configurations. Against five Transformer-based baselines from the literature, MSMixer achieves best or second-best MSE in 9 of 16 configurations while using 5x fewer parameters than PatchTST. Ablation and sensitivity analyses confirm the complementary contributions of the multi-scale branches and the DLinear shortcut.

Related papers

• VertiFuseX: Generalizable Financial Forecasting via Multi-Stream Temporal Fusion [0.0]
  We propose VertiFuseX, a hybrid LSTM architecture using penultimate-layer vertical fusion of multi-scale temporal representations.<n>We evaluate it on 15 years (2010-2024) of closing prices from 10 global equity indices using strict chronological out-of-sample testing.<n>VertiFuseX achieves 30-54% MAPE reductions and over 40% improvements in MAE and RMSE versus LSTM-based baselines.
  arXiv  Detail & Related papers  (2026-09-11T12:54:25Z)
• Towards Fast and Effective Long Video Understanding of Multimodal Large Language Models via Adaptive Quasi-Gaussian Sampling [71.62893745623526]
  Video frame selection is a problem of Quasi-Gaussian Sampling.<n>We propose an adaptive and training-free approach termed AdaQ.
  arXiv  Detail & Related papers  (2026-06-23T06:13:30Z)
• SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting [9.398256560898448]
  SEMixer is a lightweight model designed for long-term time series forecasting (TSF)<n>Mixer features a Random Attention Mechanism (RAM) and a Multiscale Progressive Mixing Chain (MPMC)<n>MPMC stacks RAM and ensemble-Mixer in a memory-efficient manner, achieving more effective temporal mixing.
  arXiv  Detail & Related papers  (2026-02-18T06:53:32Z)
• DPWMixer: Dual-Path Wavelet Mixer for Long-Term Time Series Forecasting [6.01829429039985]
  Long-term time series forecasting is a critical task in computational intelligence.<n>This paper proposes DPWMixer, a computationally efficient Dual-Path architecture.<n>Experiments on eight public benchmarks demonstrate that our method achieves a consistent improvement over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-11-30T03:12:50Z)
• MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping [52.02659589971978]
  We propose MoDES, the first training-free framework that adaptively skips experts to enable efficient and accurate MoE MLLM inference.<n>MoDES significantly enhances inference speed, improving the prefilling time by 2.16$times$ and the decoding time by 1.26$times$.
  arXiv  Detail & Related papers  (2025-11-19T18:48:27Z)
• T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion [0.4915744683251151]
  T3Time is a novel trimodal framework consisting of time, spectral, and prompt branches.<n>It learns prioritization between temporal and spectral features based on the prediction horizon.<n>Our model consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-06T09:31:44Z)
• Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity [56.0251572416922]
  State Space Models (SSMs) have emerged as efficient alternatives to Transformers for sequential modeling.<n>We propose a novel SSM architecture that introduces modality-aware sparsity through modality-specific parameterization of the Mamba block.<n>We evaluate Mixture-of-Mamba across three multi-modal pretraining settings.
  arXiv  Detail & Related papers  (2025-01-27T18:35:05Z)
• Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training [78.93900796545523]
  Mini-Sequence Transformer (MsT) is a methodology for highly efficient and accurate LLM training with extremely long sequences. MsT partitions input sequences and iteratively processes mini-sequences to reduce intermediate memory usage. integrated with the huggingface library, MsT successfully extends the maximum context length of Qwen, Mistral, and Gemma-2 by 12-24x.
  arXiv  Detail & Related papers  (2024-07-22T01:52:30Z)
• MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding [64.65145700121442]
  We introduce MM-Mixing, a multi-modal mixing alignment framework for 3D understanding. Our proposed two-stage training pipeline combines feature-level and input-level mixing to optimize the 3D encoder. We demonstrate that MM-Mixing significantly improves baseline performance across various learning scenarios.
  arXiv  Detail & Related papers  (2024-05-28T18:44:15Z)
• TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting [13.410217680999459]
  Transformers have gained popularity in time series forecasting for their ability to capture long-sequence interactions. High memory and computing requirements pose a critical bottleneck for long-term forecasting. We propose TSMixer, a lightweight neural architecture composed of multi-layer perceptron (MLP) modules.
  arXiv  Detail & Related papers  (2023-06-14T06:26:23Z)
• TriMLP: Revenge of a MLP-like Architecture in Sequential Recommendation [23.32537260687907]
  We present a sequential-like architecture for sequential recommendation, namely TriMLP, with a novel Triangular Mixer for cross-token communications. In designing Triangular Mixer, we simplify the cross-token operation inascii as the basic matrix multiplication, and drop the lower-triangle neurons of the weight matrix to block the anti-chronological order connections from future tokens.
  arXiv  Detail & Related papers  (2023-05-24T03:32:31Z)
• SplitMixer: Fat Trimmed From MLP-like Models [53.12472550578278]
  We present SplitMixer, a simple and lightweight isotropic-like architecture, for visual recognition. It contains two types of interleaving convolutional operations to mix information across locations (spatial mixing) and channels (channel mixing)
  arXiv  Detail & Related papers  (2022-07-21T01:37:07Z)

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.