Auto-ML Graph Neural Network Hypermodels for Outcome Prediction in Event-Sequence Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Fang, Kosca, Lance, Kosca, Adrienne, Gacesa, Marko, Damiani, Ernesto
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914168664227840
author Wang, Fang
Kosca, Lance
Kosca, Adrienne
Gacesa, Marko
Damiani, Ernesto
author_facet Wang, Fang
Kosca, Lance
Kosca, Adrienne
Gacesa, Marko
Damiani, Ernesto
contents This paper introduces HGNN(O), an AutoML GNN hypermodel framework for outcome prediction on event-sequence data. Building on our earlier work on graph convolutional network hypermodels, HGNN(O) extends four architectures-One Level, Two Level, Two Level Pseudo Embedding, and Two Level Embedding-across six canonical GNN operators. A self-tuning mechanism based on Bayesian optimization with pruning and early stopping enables efficient adaptation over architectures and hyperparameters without manual configuration. Empirical evaluation on both balanced and imbalanced event logs shows that HGNN(O) achieves accuracy exceeding 0.98 on the Traffic Fines dataset and weighted F1 scores up to 0.86 on the Patients dataset without explicit imbalance handling. These results demonstrate that the proposed AutoML-GNN approach provides a robust and generalizable benchmark for outcome prediction in complex event-sequence data.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18835
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Auto-ML Graph Neural Network Hypermodels for Outcome Prediction in Event-Sequence Data
Wang, Fang
Kosca, Lance
Kosca, Adrienne
Gacesa, Marko
Damiani, Ernesto
Machine Learning
This paper introduces HGNN(O), an AutoML GNN hypermodel framework for outcome prediction on event-sequence data. Building on our earlier work on graph convolutional network hypermodels, HGNN(O) extends four architectures-One Level, Two Level, Two Level Pseudo Embedding, and Two Level Embedding-across six canonical GNN operators. A self-tuning mechanism based on Bayesian optimization with pruning and early stopping enables efficient adaptation over architectures and hyperparameters without manual configuration. Empirical evaluation on both balanced and imbalanced event logs shows that HGNN(O) achieves accuracy exceeding 0.98 on the Traffic Fines dataset and weighted F1 scores up to 0.86 on the Patients dataset without explicit imbalance handling. These results demonstrate that the proposed AutoML-GNN approach provides a robust and generalizable benchmark for outcome prediction in complex event-sequence data.
title Auto-ML Graph Neural Network Hypermodels for Outcome Prediction in Event-Sequence Data
topic Machine Learning
url https://arxiv.org/abs/2511.18835