自适应调优的图神经网络工具包，用于事件序列预测
HGCN(O): A Self-Tuning GCN HyperModel Toolkit for Outcome Prediction in Event-Sequence Data
- 融合多种图结构与时间依赖关系，动态优化预测性能
- 在非平衡数据上GCNConv模型表现更优，整体稳定性强
- 适合流程挖掘、业务预测等场景，提升事件序列建模精度
我们提出HGCN(O)，一个基于图卷积网络（GCN）的自适应调优工具包，用于事件序列预测。该工具包包含四种GCN架构（O-GCN、T-GCN、TP-GCN、TE-GCN），基于GCNConv和GraphConv层，整合了不同节点与图级属性及时间依赖关系（通过边权重表示），在平衡与非平衡数据集上均提升了预测准确率与稳定性。大量实验表明，GCNConv模型在非平衡数据上表现更优，而所有模型在平衡数据上表现一致。结果证实HGCN(O)显著优于传统方法。应用场景包括预测性业务流程监控（PBPM），即根据事件日志预测未来事件或流程状态。
原文摘要 · Abstract (English)
We propose HGCN(O), a self-tuning toolkit using Graph Convolutional Network (GCN) models for event sequence prediction. Featuring four GCN architectures (O-GCN, T-GCN, TP-GCN, TE-GCN) across the GCNConv and GraphConv layers, our toolkit integrates multiple graph representations of event sequences with different choices of node- and graph-level attributes and in temporal dependencies via edge weights, optimising prediction accuracy and stability for balanced and unbalanced datasets. Extensive experiments show that GCNConv models excel on unbalanced data, while all models perform consistently on balanced data. Experiments also confirm the superior performance of HGCN(O) over traditional approaches. Applications include Predictive Business Process Monitoring (PBPM), which predicts future events or states of a business process based on event logs.
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。