arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.08473cs.LG
收藏

一种用于训练具有多面节点特征的深度图模型的鲁棒堆叠框架

A Robust Stacking Framework for Training Deep Graph Models with Multifaceted Node Features

University of Maryland(马里兰大学);Amazon(亚马逊)

Jiuhai Chen, Jonas Mueller, Vassilis N. Ioannidis, Tom Goldstein, David Wipf

摘要:

图神经网络(GNNs)与数字节点特征和图形结构作为输入已经表现出优越的性能在各种监督学习任务与图形数据。然而,GNN所使用的数值节点特征通常是从大多数真实世界应用中的文本或表格(数值/分类)类型的原始数据中提取的。在具有IID(非图)数据的大多数标准监督学习设置中,此类数据类型的最佳模型不是简单的神经网络层,因此不容易并入GNN。在这里,我们提出了一个强大的堆叠框架,融合图形感知传播与任意模型的IID数据,这是集成和堆叠在多个层。我们的分层框架利用装袋和堆叠策略来实现强大的泛化,从而有效地减轻了标签泄漏和过拟合。在具有表格/文本节点特征的各种图形数据集上,我们的方法相对于表格/文本和图神经网络模型以及现有的结合两者的最先进的混合策略实现了相当或更好的性能。

英文摘要:

Graph Neural Networks (GNNs) with numerical node features and graph structure as inputs have demonstrated superior performance on various supervised learning tasks with graph data. However the numerical node features utilized by GNNs are commonly extracted from raw data which is of text or tabular (numeric/categorical) type in most real-world applications. The best models for such data types in most standard supervised learning settings with IID (non-graph) data are not simple neural network layers and thus are not easily incorporated into a GNN. Here we propose a robust stacking framework that fuses graph-aware propagation with arbitrary models intended for IID data, which are ensembled and stacked in multiple layers. Our layer-wise framework leverages bagging and stacking strategies to enjoy strong generalization, in a manner which effectively mitigates label leakage and overfitting. Across a variety of graph datasets with tabular/text node features, our method achieves comparable or superior performance relative to both tabular/text and graph neural network models, as well as existing state-of-the-art hybrid strategies that combine the two.

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。

↑