Edge Attention-based Multi-Relational Graph Convolutional Networks
Edge Attention-based Multi-Relational Graph Convolutional Networks
复制标题
DOI：
--
复制
发表时间：
2018-02
期刊：
影响因子：
--
通讯作者：
Chao Shang;Qinqing Liu;Ko-Shin Chen;Jiangwen Sun;Jin Lu;Jinfeng Yi;J. Bi
中科院分区：
文献类型：
--
作者：
Chao Shang;Qinqing Liu;Ko-Shin Chen;Jiangwen Sun;Jin Lu;Jinfeng Yi;J. Bi
图卷积网络（GCN）是卷积神经网络（CNN）的推广，可以处理任意结构的图。二进制邻接矩阵通常用于训练GCN。最近，注意力机制允许网络学习邻域的动态和自适应聚合。我们提出了一个新的GCN模型的图，其边缘的特点是在多个视图或精确的多个关系。例如，在化学图论中，化合物结构通常由氢耗尽的分子图表示，其中节点对应于原子，边对应于化学键。多个属性对于表征化学键可能很重要，例如原子对（键连接的原子类型），芳香性以及键是否在环中。不同的属性导致相同分子的不同图形表示。在化学和机器学习领域，人们越来越感兴趣的是从分子图中直接学习化合物的分子性质，而不是从化学家预先定义的指纹中学习。所提出的GCN模型，我们称之为基于边缘注意力的多关系GCN（EAGCN），在图卷积中联合学习注意力权重和节点特征。对于每个键属性，使用实值注意矩阵来代替二进制邻接矩阵。通过为边缘注意力设计字典，并通过查找字典形成每个分子的注意力矩阵，EAGCN利用不同分子中键之间的对应关系。化合物性质的预测是基于聚合的节点特征，这是独立的变化的分子（图）的大小。我们证明了EAGCN对多个化学数据集的有效性：Tox21，HIV，Freesolv和亲脂性，并解释了由此产生的注意力权重。
Graph convolutional network (GCN) is generalization of convolutional neural network (CNN) to work with arbitrarily structured graphs. A binary adjacency matrix is commonly used in training a GCN. Recently, the attention mechanism allows the network to learn a dynamic and adaptive aggregation of the neighborhood. We propose a new GCN model on the graphs where edges are characterized in multiple views or precisely in terms of multiple relationships. For instance, in chemical graph theory, compound structures are often represented by the hydrogen-depleted molecular graph where nodes correspond to atoms and edges correspond to chemical bonds. Multiple attributes can be important to characterize chemical bonds, such as atom pair (the types of atoms that a bond connects), aromaticity, and whether a bond is in a ring. The different attributes lead to different graph representations for the same molecule. There is growing interests in both chemistry and machine learning fields to directly learn molecular properties of compounds from the molecular graph, instead of from fingerprints predefined by chemists. The proposed GCN model, which we call edge attention-based multi-relational GCN (EAGCN), jointly learns attention weights and node features in graph convolution. For each bond attribute, a real-valued attention matrix is used to replace the binary adjacency matrix. By designing a dictionary for the edge attention, and forming the attention matrix of each molecule by looking up the dictionary, the EAGCN exploits correspondence between bonds in different molecules. The prediction of compound properties is based on the aggregated node features, which is independent of the varying molecule (graph) size. We demonstrate the efficacy of the EAGCN on multiple chemical datasets: Tox21, HIV, Freesolv, and Lipophilicity, and interpret the resultant attention weights.