Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting

TL;DR

This paper introduces TCVAE, a novel framework that models distributional changes in multivariate time series to improve forecasting accuracy amidst non-stationarity and distribution drift.

Contribution

The paper proposes a temporal conditional variational autoencoder with a Hawkes attention mechanism and flow-based distribution modeling for dynamic distribution adaptation in MTS forecasting.

Findings

Outperforms state-of-the-art models on six real-world datasets.

Demonstrates robustness to distribution drift and non-stationarity.

Provides effective case studies and visualizations.

Abstract

Due to the non-stationary nature, the distribution of real-world multivariate time series (MTS) changes over time, which is known as distribution drift. Most existing MTS forecasting models greatly suffer from distribution drift and degrade the forecasting performance over time. Existing methods address distribution drift via adapting to the latest arrived data or self-correcting per the meta knowledge derived from future data. Despite their great success in MTS forecasting, these methods hardly capture the intrinsic distribution changes, especially from a distributional perspective. Accordingly, we propose a novel framework temporal conditional variational autoencoder (TCVAE) to model the dynamic distributional dependencies over time between historical observations and future data in MTSs and infer the dependencies as a temporal conditional distribution to leverage latent variables. Specifically, a novel temporal Hawkes attention mechanism represents temporal factors subsequently fed into feed-forward networks to estimate the prior Gaussian distribution of latent variables. The representation of temporal factors further dynamically adjusts the structures of Transformer-based encoder and decoder to distribution changes by leveraging a gated attention mechanism. Moreover, we introduce conditional continuous normalization flow to transform the prior Gaussian to a complex and form-free distribution to facilitate flexible inference of the temporal conditional distribution. Extensive experiments conducted on six real-world MTS datasets demonstrate the TCVAE's superior robustness and effectiveness over the state-of-the-art MTS forecasting baselines. We further illustrate the TCVAE applicability through multifaceted case studies and visualization in real-world scenarios.