PAMNet: Cycle-aware Phase-Amplitude Modulation Network for Multivariate Time Series Forecasting

TL;DR

PAMNet introduces a cycle-aware model that explicitly decomposes multivariate time series into phase and amplitude components, improving forecasting accuracy by capturing intrinsic periodic patterns more effectively.

Contribution

It proposes a novel dual-branch modulator with dedicated embeddings for phase and amplitude, explicitly modeling their interaction without complex attention mechanisms.

Findings

Achieves state-of-the-art performance on twelve real-world datasets.

Effectively captures phase-dependent mean shifts and amplitude variations.

Outperforms existing methods in multivariate time series forecasting.

Abstract

Reliable periodic patterns serve as a fundamental basis for accurate multivariate time series forecasting. However, existing methods either implicitly extract periodicity through complex model architectures (e.g., Transformers) with high computational overhead or overlook the intrinsic phase-amplitude coupling when modeling periodic components explicitly. To address these issues, we propose a novel Cycle-aware Phase-Amplitude Modulation Network (PAMNet) that explicitly decomposes periodic patterns into complementary phase and amplitude components. The core innovation lies in its dual-branch modulator, featuring dedicated learnable embeddings for phase positioning and amplitude modulation. The phase branch employs cyclical embeddings to capture phase-dependent mean shifts, while the amplitude branch models intensity variations to adapt to changes in variance. A lightweight modulator with element-wise fusion efficiently combines these components, enabling explicit modeling of their interactions without complex attention mechanisms. Extensive experiments on twelve real-world datasets demonstrate that our method achieves state-of-the-art performance through its novel phase-amplitude decoupling mechanism, offering a new perspective for cyclical modeling in time series forecasting.