arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.11860cs.LG
收藏

图半监督学习的循环标号传播

Cyclic Label Propagation for Graph Semi-supervised Learning

Alibaba Group(阿里巴巴集团);Monash University(莫纳什大学);Central South University(中南大学);Zhejiang University(浙江大学)

Zhao Li, Yixin Liu, Zhen Zhang, Shirui Pan, Jianliang Gao, Jiajun Bu

摘要:

图神经网络(GNN)已经成为图分析的有效方法,特别是在半监督学习的情况下。尽管GNN取得了成功,但它经常遭受过平滑和过拟合问题,这影响了它在节点分类任务上的性能。我们分析了一种替代方法,标签传播算法(LPA),避免了上述问题,因此它是一个有前途的选择图半监督学习。然而,LPA在特征开发和关系建模方面的固有局限性使得标签传播变得不那么有效。为了克服这些限制,我们引入了一种新的图半监督学习框架,称为循环标签传播(CycProp),它将GNN以循环和相互加强的方式集成到标签传播过程中,以利用GNN和LPA的优势。特别地,我们提出的CycProp使用标签传播的增强信息更新GNN模块学习的节点嵌入,同时依次在节点嵌入的帮助下微调标签传播的加权图。在模型收敛后,分别使用LPA和GNN模块获得可靠的预测标签和信息节点嵌入。在各种真实数据集上进行了大量的实验,实验结果表明,所提出的CycProp模型可以实现相对显着的收益比国家的最先进的方法。

英文摘要:

Graph neural networks (GNNs) have emerged as effective approaches for graph analysis, especially in the scenario of semi-supervised learning. Despite its success, GNN often suffers from over-smoothing and over-fitting problems, which affects its performance on node classification tasks. We analyze that an alternative method, the label propagation algorithm (LPA), avoids the aforementioned problems thus it is a promising choice for graph semi-supervised learning. Nevertheless, the intrinsic limitations of LPA on feature exploitation and relation modeling make propagating labels become less effective. To overcome these limitations, we introduce a novel framework for graph semi-supervised learning termed as Cyclic Label Propagation (CycProp for abbreviation), which integrates GNNs into the process of label propagation in a cyclic and mutually reinforcing manner to exploit the advantages of both GNNs and LPA. In particular, our proposed CycProp updates the node embeddings learned by GNN module with the augmented information by label propagation, while fine-tunes the weighted graph of label propagation with the help of node embedding in turn. After the model converges, reliably predicted labels and informative node embeddings are obtained with the LPA and GNN modules respectively. Extensive experiments on various real-world datasets are conducted, and the experimental results empirically demonstrate that the proposed CycProp model can achieve relatively significant gains over the state-of-the-art methods.

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。

↑