TempoKGAT: A Novel Graph Attention Network Approach for Temporal Graph Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sasal, Lena, Busby, Daniel, Hadid, Abdenour
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915076592631808
author Sasal, Lena
Busby, Daniel
Hadid, Abdenour
author_facet Sasal, Lena
Busby, Daniel
Hadid, Abdenour
contents Graph neural networks (GNN) have shown significant capabilities in handling structured data, yet their application to dynamic, temporal data remains limited. This paper presents a new type of graph attention network, called TempoKGAT, which combines time-decaying weight and a selective neighbor aggregation mechanism on the spatial domain, which helps uncover latent patterns in the graph data. In this approach, a top-k neighbor selection based on the edge weights is introduced to represent the evolving features of the graph data. We evaluated the performance of our TempoKGAT on multiple datasets from the traffic, energy, and health sectors involving spatio-temporal data. We compared the performance of our approach to several state-of-the-art methods found in the literature on several open-source datasets. Our method shows superior accuracy on all datasets. These results indicate that TempoKGAT builds on existing methodologies to optimize prediction accuracy and provide new insights into model interpretation in temporal contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2408_16391
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TempoKGAT: A Novel Graph Attention Network Approach for Temporal Graph Analysis
Sasal, Lena
Busby, Daniel
Hadid, Abdenour
Machine Learning
Graph neural networks (GNN) have shown significant capabilities in handling structured data, yet their application to dynamic, temporal data remains limited. This paper presents a new type of graph attention network, called TempoKGAT, which combines time-decaying weight and a selective neighbor aggregation mechanism on the spatial domain, which helps uncover latent patterns in the graph data. In this approach, a top-k neighbor selection based on the edge weights is introduced to represent the evolving features of the graph data. We evaluated the performance of our TempoKGAT on multiple datasets from the traffic, energy, and health sectors involving spatio-temporal data. We compared the performance of our approach to several state-of-the-art methods found in the literature on several open-source datasets. Our method shows superior accuracy on all datasets. These results indicate that TempoKGAT builds on existing methodologies to optimize prediction accuracy and provide new insights into model interpretation in temporal contexts.
title TempoKGAT: A Novel Graph Attention Network Approach for Temporal Graph Analysis
topic Machine Learning
url https://arxiv.org/abs/2408.16391