Local Ai
MSTN: A Lightweight and Fast Model for General TimeSeries Analysis
arXiv:2511.20577v3 Announce Type: replace Abstract: Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, fr
arXiv:2511.20577v3 Announce Type: replace Abstract: Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many contemporary architectures impose rigid, fixed-scale structural priors -- such as patch-based tokenization, predefined receptive fields, or frozen backbone encoders -- which can over-regularize temporal dynamics and limit adaptability to abrupt high-magnitude events. To handle this, we introduce the Multi-scale Temporal Network (MSTN), a hybrid neural architecture grounded in an Early Temporal Aggregation principle. MSTN integrates three complementary components: (i) a multi-scale convolutional encoder that captures fine-grained local structure; (ii) a sequence modeling module that learns long-range dependencies through either recurrent or attention-based mechanisms; and (iii) a self-gated fusion stage incorporating squeeze-excitation and a single dense layer to dynamically reweight and fuse multi-scale representations. This design enables MSTN to flexibly model temporal patterns spanning milliseconds to extended horizons, while avoiding the computational burden typically associated with long-context models. Across extensive benchmarks covering imputation, long term forecasting, short term forecasting, classification, and cross-dataset generalization, MSTN achieves state-of-the-art performance, establishing new best results on 33 of 40 datasets, while remaining lightweight (sim278,520 params for MSTN-BiLSTM and sim950,776 approx 1M for MSTN-Transformer) and suitable for low-latency inference (<1 sec, often in milliseconds), resource-constrained deployment.
Related
- Temporal Patch Shuffle (TPS): Leveraging Patch-Level Shuffling to Boost Generalization and Robustness in Time Series Forecasting
- Sheaf Diffusion with Adaptive Local Structure for Spatio-Temporal Forecasting
- Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment
- A Weak Penalty Neural ODE for Learning Chaotic Dynamics from Noisy Time Series
- Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly Detection
Source: arXiv cs.LG | 2026-04-14