HPMixer: Hierarchical Patching for Multivariate Time Series Forecasting

2026-02-18 · Jung Min Choi, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme arxiv

In long-term multivariate time series forecasting, effectively capturing both periodic patterns and residual dynamics is essential. To address this within standard deep learning benchmark settings, we propose the Hierarchical Patching Mixer (HPMixer), which models periodicity and residuals in a decoupled yet complementary manner. The periodic component utilizes a learnable cycle module [7] enhanced with a nonlinear channel-wise MLP for greater expressiveness. The residual component is processed through a Learnable Stationary Wavelet Transform (LSWT) to extract stable, shift-invariant frequency-domain representations. Subsequently, a channel-mixing encoder models explicit inter-channel dependencies, while a two-level non-overlapping hierarchical patching mechanism captures coarse- and fine-scale residual variations. By integrating decoupled periodicity modeling with structured, multi-scale residual learning, HPMixer provides an effective framework. Extensive experiments on standard multivariate benchmarks demonstrate that HPMixer achieves competitive or state-of-the-art performance compared to recent baselines.

📄 PDF Abstract BibTeX arXiv:2602.16468

Code (0)

등록된 구현이 없습니다.

Tasks

Multivariate Time Series Forecasting

TimeSQL: Improving Multivariate Time Series Forecasting with Multi-Scale Patching and Smooth Quadratic Loss

2023-11-19 · Site Mo, Haoxin Wang, Bixiong Li, Songhai Fan 외

Time series is a special type of sequence data, a sequence of real-valued random variables collected at even intervals of time. The real-world multivariate time series comes with noises and contains complicated local and…

Multivariate Time Series Forecasting Time Series Time Series Forecasting

Two-Stage Aggregation with Dynamic Local Attention for Irregular Time Series

2023-11-13 · Xingyu Chen, Xiaochen Zheng, Amina Mollaysa, Manuel Schürch 외

Irregular multivariate time series data is characterized by varying time intervals between consecutive observations of measured variables/signals (i.e., features) and varying sampling rates (i.e., recordings/measurement)…

Irregular Time Series Time Series

Using Pre-trained LLMs for Multivariate Time Series Forecasting

2025-01-10 · Malcolm L. Wolff, Shenghao Yang, Kari Torkkola, Michael W. Mahoney

Pre-trained Large Language Models (LLMs) encapsulate large amounts of knowledge and take enormous amounts of compute to train. We make use of this resource, together with the observation that LLMs are able to transfer kn…

Decoder Multivariate Time Series Forecasting Time Series Time Series Forecasting

TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching

2026-06-02 · Zhe Li, Jindong Tian, Hao Miao, Zhi Lei 외 arxiv

Multivariate time series forecasting plays a critical role in real-world applications, including weather prediction, stock analysis, and health monitoring. Due to the diversity of data sources, time series exhibit divers…

Multivariate Time Series Forecasting

SiamTST: A Novel Representation Learning Framework for Enhanced Multivariate Time Series Forecasting applied to Telco Networks

2024-07-02 · Simen Kristoffersen, Peter Skaar Nordby, Sara Malacarne, Massimiliano Ruocco 외

We introduce SiamTST, a novel representation learning framework for multivariate time series. SiamTST integrates a Siamese network with attention, channel-independent patching, and normalization techniques to achieve sup…

Multivariate Time Series Forecasting Representation Learning Time Series Time Series Forecasting