arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2302.09755cs.LGcs.SI
收藏

基于置信度子图匹配寻找异配邻居用于半监督节点分类

Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classification

Seoul National University(首尔国立大学);Korea Institute of Energy Technology(韩国能源技术研究院)

Yoonhyuk Choi, Jiho Choi, Taewook Ko, Chong-Kwon Kim

AI总结:

本文提出一种两阶段算法,通过基于置信度比率的子图匹配识别并利用异配邻居的边系数,改进GNN标签传播机制,以缓解过度平滑并提升半监督节点分类性能。

摘要:

图神经网络(GNNs)在许多基于图的应用中已被证明是强大的。然而,它们在异配设置下无法很好地泛化,即邻居节点具有不同标签的情形。为应对这一挑战,我们采用置信度比率作为超参数,假设部分边是非同配的(异配的)。在此,我们提出一个两阶段算法。首先,我们通过使用一个补充模块进行子图匹配来确定边系数。然后,我们应用带有改进标签传播机制的GNNs来有效利用边系数。具体而言,我们的补充模块根据给定的置信度比率识别出一定比例的任务无关边。利用剩余边,我们采用广泛使用的最优传输来度量两个节点及其子图之间的相似性。最后,利用这些系数作为GNNs上的补充信息,我们改进了标签传播机制,从而可以防止权重较小的两个节点变得更接近。在基准数据集上的实验表明,我们的模型缓解了过度平滑问题并提升了性能。

英文摘要:

Graph Neural Networks (GNNs) have proven to be powerful in many graph-based applications. However, they fail to generalize well under heterophilic setups, where neighbor nodes have different labels. To address this challenge, we employ a confidence ratio as a hyper-parameter, assuming that some of the edges are disassortative (heterophilic). Here, we propose a two-phased algorithm. Firstly, we determine edge coefficients through subgraph matching using a supplementary module. Then, we apply GNNs with a modified label propagation mechanism to utilize the edge coefficients effectively. Specifically, our supplementary module identifies a certain proportion of task-irrelevant edges based on a given confidence ratio. Using the remaining edges, we employ the widely used optimal transport to measure the similarity between two nodes with their subgraphs. Finally, using the coefficients as supplementary information on GNNs, we improve the label propagation mechanism which can prevent two nodes with smaller weights from being closer. The experiments on benchmark datasets show that our model alleviates over-smoothing and improves performance.

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。

↑