DeepHGNN: Study of Graph Neural Network based Forecasting Methods for Hierarchically Related Multivariate Time Series

TL;DR

DeepHGNN introduces a hierarchical graph neural network framework that improves forecasting accuracy across complex hierarchical multivariate time series by leveraging graph-based interpolation and reconciliation mechanisms.

Contribution

It presents a novel hierarchical GNN architecture with graph-based interpolation and reconciliation, enhancing forecast accuracy and coherence across hierarchical levels.

Findings

DeepHGNN outperforms state-of-the-art models in accuracy.

The model effectively captures intra- and inter-series relationships.

Hierarchical pooling improves forecast reliability.

Abstract

Graph Neural Networks (GNN) have gained significant traction in the forecasting domain, especially for their capacity to simultaneously account for intra-series temporal correlations and inter-series relationships. This paper introduces a novel Hierarchical GNN (DeepHGNN) framework, explicitly designed for forecasting in complex hierarchical structures. The uniqueness of DeepHGNN lies in its innovative graph-based hierarchical interpolation and an end-to-end reconciliation mechanism. This approach ensures forecast accuracy and coherence across various hierarchical levels while sharing signals across them, addressing a key challenge in hierarchical forecasting. A critical insight in hierarchical time series is the variance in forecastability across levels, with upper levels typically presenting more predictable components. DeepHGNN capitalizes on this insight by pooling and leveraging knowledge from all hierarchy levels, thereby enhancing the overall forecast accuracy. Our comprehensive evaluation set against several state-of-the-art models confirm the superior performance of DeepHGNN. This research not only demonstrates DeepHGNN's effectiveness in achieving significantly improved forecast accuracy but also contributes to the understanding of graph-based methods in hierarchical time series forecasting.