arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.12920cs.LG
收藏

可解释图神经网络的学习稀疏化

Learnt Sparsification for Interpretable Graph Neural Networks

L3S Research Center(L3S研究中心)

Mandeep Rathee, Zijian Zhang, Thorben Funke, Megha Khosla, Avishek Anand

摘要:

图神经网络(GNN)在需要关系建模的各种任务和领域取得了巨大成功。GNN使用图结构聚合节点特征作为归纳偏差,从而产生灵活而强大的模型。然而,GNN仍然很难解释,因为节点特征和图结构之间的相互作用只是隐式学习的。在本文中,我们提出了一种新的方法,称为Kedge显式稀疏的基础图,通过删除不必要的邻居。我们的主要思想是基于一种易于处理的稀疏化方法,使用Hard Kumaraswamy分布,可以与任何GNN模型结合使用。Kedge以模块化的方式学习边缘掩码,使用任何GNN进行训练,允许以端到端的方式进行基于梯度的优化。我们通过大量的实验证明,我们的模型Kedge可以修剪很大比例的边缘,只有一个很小的影响测试精度。具体来说,在PubMed数据集中,Kedge学习丢弃超过80%的边,准确率仅下降2%,这表明与节点特征相比,图结构的贡献很小。最后,我们还表明,Kedge通过随着GNN层的增加而保持良好的任务性能,有效地对抗了深度GNN中的过度平滑现象。

英文摘要:

Graph neural networks (GNNs) have achieved great success on various tasks and fields that require relational modeling. GNNs aggregate node features using the graph structure as inductive biases resulting in flexible and powerful models. However, GNNs remain hard to interpret as the interplay between node features and graph structure is only implicitly learned. In this paper, we propose a novel method called Kedge for explicitly sparsifying the underlying graph by removing unnecessary neighbors. Our key idea is based on a tractable method for sparsification using the Hard Kumaraswamy distribution that can be used in conjugation with any GNN model. Kedge learns edge masks in a modular fashion trained with any GNN allowing for gradient based optimization in an end-to-end fashion. We demonstrate through extensive experiments that our model Kedge can prune a large proportion of the edges with only a minor effect on the test accuracy. Specifically, in the PubMed dataset, Kedge learns to drop more than 80% of the edges with an accuracy drop of merely 2% showing that graph structure has only a small contribution in comparison to node features. Finally, we also show that Kedge effectively counters the over-smoothing phenomena in deep GNNs by maintaining good task performance with increasing GNN layers.

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。

↑