基于路径特征的梯度提升法，高效实现图级预测。
Path-Based Gradient Boosting for Graph-Level Prediction
- 从图结构直接学习判别性路径特征，结合梯度提升优化
- 在多个数据集上表现优于或媲美GNN与图核方法
- 自动选择起点节点，适合节点数较多的图数据
我们提出PathBoost，一种用于图级分类与回归的梯度树提升方法，可直接从输入图结构中学习判别性路径特征。在先前针对特定化学应用的工作基础上，PathBoost引入三项关键扩展：(i) 通过逻辑损失函数适配二分类任务；(ii) 通过前缀分解将多种节点与边属性融入路径特征空间；(iii) 基于类别属性多样性自动选择锚点节点，无需用户指定路径起始点。我们在多个基准数据集上将PathBoost与图神经网络及图核方法对比，一半数据集结果更优，其余表现相当。在平均节点数较大的图上性能更突出。结果表明，路径增强的提升方法可与复杂黑箱模型相竞争。
原文摘要 · Abstract (English)
We propose PathBoost, a gradient tree boosting method for graph-level classification and regression that learns discriminative path-based features directly from the input graph structure. Building on a previous work, which was tailored to a specific chemistry application, PathBoost introduces three key extensions: (i) adaptation to binary classification through gradient boosting with a logistic loss, (ii) incorporation of multiple node and edge attributes into the path feature space via a prefix-based decomposition, and (iii) automatic anchor node selection based on categorical attribute diversity, eliminating the need for the user to specify the starting point of the considered path features. We compared PathBoost to graph neural networks and graph kernel approaches on several benchmark datasets, obtaining better results in half of them, and comparable results in the rest. PathBoost shows better performances on graphs with larger average node counts. Overall, the results demonstrate that path-based boosting methods can be competitive with more complex black-box approaches.
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。