Saved in:
Bibliographic Details
Main Authors: Bailie, Thomas, Koh, Yun Sing, Mukkavilli, S. Karthik, Vetrova, Varvara
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.00349
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910902377250816
author Bailie, Thomas
Koh, Yun Sing
Mukkavilli, S. Karthik
Vetrova, Varvara
author_facet Bailie, Thomas
Koh, Yun Sing
Mukkavilli, S. Karthik
Vetrova, Varvara
contents Graphical forecasting models learn the structure of time series data via projecting onto a graph, with recent techniques capturing spatial-temporal associations between variables via edge weights. Hierarchical variants offer a distinct advantage by analysing the time series across multiple resolutions, making them particularly effective in tasks like global weather forecasting, where low-resolution variable interactions are significant. A critical challenge in hierarchical models is information loss during forward or backward passes through the hierarchy. We propose the Hierarchical Graph Flow (HiGFlow) network, which introduces a memory buffer variable of dynamic size to store previously seen information across variable resolutions. We theoretically show two key results: HiGFlow reduces smoothness when mapping onto new feature spaces in the hierarchy and non-strictly enhances the utility of message-passing by improving Weisfeiler-Lehman (WL) expressivity. Empirical results demonstrate that HiGFlow outperforms state-of-the-art baselines, including transformer models, by at least an average of 6.1% in MAE and 6.2% in RMSE. Code is available at https://github.com/TB862/ HiGFlow.git.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00349
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reducing Smoothness with Expressive Memory Enhanced Hierarchical Graph Neural Networks
Bailie, Thomas
Koh, Yun Sing
Mukkavilli, S. Karthik
Vetrova, Varvara
Machine Learning
Graphical forecasting models learn the structure of time series data via projecting onto a graph, with recent techniques capturing spatial-temporal associations between variables via edge weights. Hierarchical variants offer a distinct advantage by analysing the time series across multiple resolutions, making them particularly effective in tasks like global weather forecasting, where low-resolution variable interactions are significant. A critical challenge in hierarchical models is information loss during forward or backward passes through the hierarchy. We propose the Hierarchical Graph Flow (HiGFlow) network, which introduces a memory buffer variable of dynamic size to store previously seen information across variable resolutions. We theoretically show two key results: HiGFlow reduces smoothness when mapping onto new feature spaces in the hierarchy and non-strictly enhances the utility of message-passing by improving Weisfeiler-Lehman (WL) expressivity. Empirical results demonstrate that HiGFlow outperforms state-of-the-art baselines, including transformer models, by at least an average of 6.1% in MAE and 6.2% in RMSE. Code is available at https://github.com/TB862/ HiGFlow.git.
title Reducing Smoothness with Expressive Memory Enhanced Hierarchical Graph Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2504.00349