arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.06750cs.LG
收藏

图分类的二次GCN

Quadratic GCN for Graph Classification

Bar-Ilan University(巴伊兰大学)

Omer Nagar, Shoval Frydman, Ori Hochman, Yoram Louzoun

摘要:

图卷积网络(GCN)已被广泛用于图中的顶点分类,并已被证明优于其他顶点分类方法。GCN已经扩展到图分类任务(GCT)。在GCT中,具有不同边数和顶点数的图属于不同的类,并且人们试图预测图类。基于GCN的GCT主要使用池化和基于注意力的模型。现有的GCT方法的精度仍然有限。在这里,我们提出了一种新的解决方案,结合GCN,知识图谱的方法,和一个新的自正则化激活函数,显着提高GCN的GCT的准确性。我们提出了二次GCN(QGCN)-一个GCN形式主义与二次层。这样的层产生具有固定维度的输出,与图顶点数无关。我们将这种方法应用到广泛的图形分类问题,并表明,当使用一个自我正则化的激活函数,QGCN优于所有的图形分类任务测试或没有外部输入的每个图形的最先进的方法。QGCN的代码可在https://github.com/Unknown-Data/QGCN上获得。

英文摘要:

Graph Convolutional Networks (GCNs) have been extensively used to classify vertices in graphs and have been shown to outperform other vertex classification methods. GCNs have been extended to graph classification tasks (GCT). In GCT, graphs with different numbers of edges and vertices belong to different classes, and one attempts to predict the graph class. GCN based GCT have mostly used pooling and attention-based models. The accuracy of existing GCT methods is still limited. We here propose a novel solution combining GCN, methods from knowledge graphs, and a new self-regularized activation function to significantly improve the accuracy of the GCN based GCT. We present quadratic GCN (QGCN) - A GCN formalism with a quadratic layer. Such a layer produces an output with fixed dimensions, independent of the graph vertex number. We applied this method to a wide range of graph classification problems, and show that when using a self regularized activation function, QGCN outperforms the state of the art methods for all graph classification tasks tested with or without external input on each graph. The code for QGCN is available at: https://github.com/Unknown-Data/QGCN .

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。

↑