用于事件序列数据结果预测的自动机器学习图神经网络超模型
Auto-ML Graph Neural Network Hypermodels for Outcome Prediction in Event-Sequence Data
AI总结:
本文提出HGNN(O)框架,通过自调机制实现高效适应,用于事件序列数据结果预测,取得高准确率和F1分数。
摘要:
本文介绍HGNN(O),一种用于事件序列数据结果预测的AutoML图神经网络超模型框架。在我们之前关于图卷积网络超模型的工作基础上,HGNN(O)扩展了四种架构——单层、双层、双层伪嵌入和双层嵌入——跨越六个标准图神经网络操作符。基于贝叶斯优化的自调机制,结合剪枝和早停,使模型能够高效适应架构和超参数,而无需手动配置。在平衡和不平衡事件日志上的实证评估显示,HGNN(O)在交通罚款数据集上实现了超过0.98的准确率,在患者数据集上实现了高达0.86的加权F1分数,而无需显式处理不平衡问题。这些结果表明,所提出的AutoML-GNN方法为复杂事件序列数据的结果预测提供了一个稳健且通用的基准。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。