SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting

TL;DR

SEMixer is a lightweight multiscale model that enhances long-term time series forecasting by capturing diverse multi-scale dependencies through novel attention and mixing mechanisms, outperforming existing methods on multiple datasets.

Contribution

The paper introduces SEMixer, a novel multiscale model with Random Attention Mechanism and Multiscale Progressive Mixing Chain, improving multi-scale dependency modeling in long-term TSF.

Findings

Validated on 10 public datasets showing superior performance.

Achieved third place in 2025 CCF AlOps Challenge.

Effective multiscale modeling with reduced noise and semantic gaps.

Abstract

Modeling multiscale patterns is crucial for long-term time series forecasting (TSF). However, redundancy and noise in time series, together with semantic gaps between non-adjacent scales, make the efficient alignment and integration of multi-scale temporal dependencies challenging. To address this, we propose SEMixer, a lightweight multiscale model designed for long-term TSF. SEMixer features two key components: a Random Attention Mechanism (RAM) and a Multiscale Progressive Mixing Chain (MPMC). RAM captures diverse time-patch interactions during training and aggregates them via dropout ensemble at inference, enhancing patch-level semantics and enabling MLP-Mixer to better model multi-scale dependencies. MPMC further stacks RAM and MLP-Mixer in a memory-efficient manner, achieving more effective temporal mixing. It addresses semantic gaps across scales and facilitates better multiscale modeling and forecasting performance. We not only validate the effectiveness of SEMixer on 10 public datasets, but also on the \textit{2025 CCF AlOps Challenge} based on 21GB real wireless network data, where SEMixer achieves third place. The code is available at the link https://github.com/Meteor-Stars/SEMixer.