arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.13312cs.LGcs.SI
收藏

基于有效特征分解的异构网络图自适应

Effective Eigendecomposition based Graph Adaptation for Heterophilic Networks

Microsoft Research India(微软印度研究院)

Vijay Lingam, Rahul Ragesh, Arun Iyer, Sundararajan Sellamanickam

摘要:

图神经网络(GNNs)在图具有强同构性(即连通节点具有相同的标号)时表现出优异的性能。然而,他们表现不佳的heterophilic图。有几种方法通过提出模型来解决异质性问题,这些模型通过使用标记数据优化特定于任务的损失函数来适应图。这些适应是通过注意力或根据手头任务的需要衰减或增强各种低频/高频信号来实现的。最近的方法调整了图的特征值。这种适应的一个重要解释是,这些模型选择/加权图的特征向量。基于这种解释,我们提出了一种基于特征分解的方法,并提出了特征网络模型,提高了GNN在异嗜图上的性能。通过学习灵活的图自适应函数来实现性能改进,这些函数调制图的特征值。通过参数共享对这些函数进行正则化有助于进一步提高性能。我们的方法实现了高达11%的改进性能的最先进的方法对heterophilic图。

英文摘要:

Graph Neural Networks (GNNs) exhibit excellent performance when graphs have strong homophily property, i.e. connected nodes have the same labels. However, they perform poorly on heterophilic graphs. Several approaches address the issue of heterophily by proposing models that adapt the graph by optimizing task-specific loss function using labelled data. These adaptations are made either via attention or by attenuating or enhancing various low-frequency/high-frequency signals, as needed for the task at hand. More recent approaches adapt the eigenvalues of the graph. One important interpretation of this adaptation is that these models select/weigh the eigenvectors of the graph. Based on this interpretation, we present an eigendecomposition based approach and propose EigenNetwork models that improve the performance of GNNs on heterophilic graphs. Performance improvement is achieved by learning flexible graph adaptation functions that modulate the eigenvalues of the graph. Regularization of these functions via parameter sharing helps to improve the performance even more. Our approach achieves up to 11% improvement in performance over the state-of-the-art methods on heterophilic graphs.

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。

↑