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

TL;DR

This paper presents HGNN(O), an AutoML framework for optimizing graph neural network hypermodels to predict outcomes from event-sequence data, demonstrating high accuracy and robustness across diverse datasets.

Contribution

Introduces a novel AutoML GNN hypermodel framework with multiple architectures and a Bayesian optimization-based self-tuning mechanism for outcome prediction.

Findings

Achieves over 0.98 accuracy on Traffic Fines dataset.

Attains up to 0.86 weighted F1 score on Patients dataset.

Demonstrates robustness on both balanced and imbalanced event logs.

Abstract

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.