Gaussian Process Latent Variable Modeling for Few-shot Time Series Forecasting

TL;DR

MetaGP is a novel meta-learning Gaussian process model that effectively captures long-term dependencies and meta-knowledge in few-shot time series forecasting, achieving state-of-the-art accuracy and interpretability.

Contribution

The paper introduces MetaGP, combining Gaussian processes with meta-learning and Kernel Association Search to improve few-shot time series forecasting.

Findings

MetaGP achieves state-of-the-art prediction accuracy.

MetaGP captures long-term dependencies effectively.

MetaGP models meta-knowledge for interpretability.

Abstract

Accurate time series forecasting is crucial for optimizing resource allocation, industrial production, and urban management, particularly with the growth of cyber-physical and IoT systems. However, limited training sample availability in fields like physics and biology poses significant challenges. Existing models struggle to capture long-term dependencies and to model diverse meta-knowledge explicitly in few-shot scenarios. To address these issues, we propose MetaGP, a meta-learning-based Gaussian process latent variable model that uses a Gaussian process kernel function to capture long-term dependencies and to maintain strong correlations in time series. We also introduce Kernel Association Search (KAS) as a novel meta-learning component to explicitly model meta-knowledge, thereby enhancing both interpretability and prediction accuracy. We study MetaGP on simulated and real-world few-shot datasets, showing that it is capable of state-of-the-art prediction accuracy. We also find that MetaGP can capture long-term dependencies and can model meta-knowledge, thereby providing valuable insights into complex time series patterns.