自动调参的图神经网络框架，精准预测事件序列结果。
Auto-ML Graph Neural Network Hypermodels for Outcome Prediction in Event-Sequence Data
- 用贝叶斯优化自适应调整模型架构与超参数。
- 交通罚单数据准确率超0.98，患者数据加权F1达0.86。
- 无需人工调参，适合复杂事件序列预测任务。
本文提出HGNN(O)，一种面向事件序列数据结果预测的AutoML图神经网络超模型框架。在先前图卷积网络超模型工作的基础上，HGNN(O)将四种架构——单层、双层、伪嵌入双层和嵌入双层——扩展至六种标准GNN算子。基于贝叶斯优化的自调参机制结合剪枝与早停策略，实现无需人工配置的高效架构与超参数适配。在平衡与非平衡事件日志上的实证评估显示，该方法在交通罚单数据集上准确率超过0.98，在患者数据集上加权F1最高达0.86，且未显式处理数据不平衡问题。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鲁棒且可泛化的基准。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。