Three-Stage Learning Unlocks Strong Performance in Simple Models for Long-Term Time Series Forecasting

TL;DR

This paper introduces STAIR, a three-stage training paradigm that enhances simple models for long-term time series forecasting by progressively capturing shared and variable-specific dynamics without complex architectures.

Contribution

The paper proposes a novel three-stage training framework, STAIR, that improves simple temporal models for long-term forecasting by structured training and residual learning, avoiding complex modules.

Findings

STAIR matches or outperforms recent strong baselines on nine benchmarks.

The approach effectively captures shared and variable-specific dynamics.

Maintains simplicity of the core temporal predictor.

Abstract

Recent studies on long-term time series forecasting have shown that simple linear models and MLP-based predictors can achieve strong performance without increasingly complex architectures. However, many competitive baselines still rely on structural priors such as frequency-domain modeling, explicit decomposition, multi-scale mixing, or sophisticated cross-variable interaction modules, while paying less attention to how simple temporal mappings should be trained and organized. In this paper, we propose STAIR, short for Stagewise Temporal Adaptation via Individualization and Residual Learning, a training paradigm for long-term time series forecasting that aims to unlock the capacity of simple temporal mapping models without introducing complex architectural modules. STAIR decomposes forecasting ability into three progressive stages: it first learns common temporal dynamics across variables through a shared temporal mapping, then adapts the shared model to each variable via channel-wise fine-tuning to capture variable-specific patterns, and finally complements the backbone with cross-variable information through residual learning. We further introduce Shared-to-Individual Fine-tuning and alpha-RevIN to mitigate the limitations of strict channel independence and the overly strong normalization prior induced by standard RevIN. This design gradually increases modeling flexibility while keeping the core temporal predictor as a shallow MLP in the main experiments, with linear variants analyzed separately. Experiments on nine long-term forecasting benchmarks show that STAIR matches or outperforms recent strong baselines while preserving a simple temporal backbone, providing a concise and effective modeling perspective for long-term time series forecasting.