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 1809.01090cs.LGstat.ML
收藏

基于量子顶点显著性的图卷积神经网络

Graph Convolutional Neural Networks based on Quantum Vertex Saliency

Central University of Finance and Economics(中央财经大学);Southern University of Science and Technology(南方科技大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of York(约克大学)

Lu Bai, Yuhang Jiao, Luca Rossi, Lixin Cui, Jian Cheng, Edwin R. Hancock

AI总结:

本文提出量子空间图卷积神经网络(QSGCNN),通过量子空间图卷积提取多尺度顶点特征并结合传统卷积层实现端到端图分类,解决了现有模型中信息丢失和不精确表示的问题。

摘要:

本文提出了一种新的量子空间图卷积神经网络(QSGCNN)模型,该模型能够直接学习任意大小图的分类函数。与最先进的图卷积神经网络(GCNN)模型不同,所提出的 QSGCNN 模型包含了识别图之间传递对齐顶点的过程,并将任意大小的图转换为固定大小的对齐顶点网格结构。为了学习具有代表性的图特征,提出并采用了一种新的量子空间图卷积,通过每个图的网格顶点之间的量子信息传播来提取多尺度顶点特征。由于量子空间卷积保留了输入顶点的网格结构(即卷积层不改变顶点的原始空间序列),所提出的 QSGCNN 模型允许直接采用传统的卷积神经网络架构来进一步学习全局图拓扑,提供了一个端到端的深度学习架构,该架构集成了量子空间图卷积层和传统卷积层中的图表示与学习以进行图分类。我们展示了所提出的 QSGCNN 模型相对于现有最先进方法的有效性。所提出的 QSGCNN 模型解决了现有 GCN 模型中由于使用 SortPooling 或 SumPooling 层而产生的信息丢失和不精确信息表示的缺点。在基准图分类数据集上的实验证明了所提出的 QSGCNN 模型的有效性。

英文摘要:

This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN) models, the proposed QSGCNN model incorporates the process of identifying transitive aligned vertices between graphs, and transforms arbitrary sized graphs into fixed-sized aligned vertex grid structures. In order to learn representative graph characteristics, a new quantum spatial graph convolution is proposed and employed to extract multi-scale vertex features, in terms of quantum information propagation between grid vertices of each graph. Since the quantum spatial convolution preserves the grid structures of the input vertices (i.e., the convolution layer does not change the original spatial sequence of vertices), the proposed QSGCNN model allows to directly employ the traditional convolutional neural network architecture to further learn from the global graph topology, providing an end-to-end deep learning architecture that integrates the graph representation and learning in the quantum spatial graph convolution layer and the traditional convolutional layer for graph classifications. We demonstrate the effectiveness of the proposed QSGCNN model in relation to existing state-of-the-art methods. The proposed QSGCNN model addresses the shortcomings of information loss and imprecise information representation arising in existing GCN models associated with the use of SortPooling or SumPooling layers. Experiments on benchmark graph classification datasets demonstrate the effectiveness of the proposed QSGCNN model.

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。

↑