Long-short Distance Aggregation Networks for Positive Unlabeled Graph Learning
Long-short Distance Aggregation Networks for Positive Unlabeled Graph Learning
复制标题
DOI：
10.1145/3357384.3358122
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Man Wu;Shirui Pan;Lan Du;I. Tsang;Xingquan Zhu;Bo Du
中科院分区：
文献类型：
--
作者：
Man Wu;Shirui Pan;Lan Du;I. Tsang;Xingquan Zhu;Bo Du
图神经网络是用来表示网络节点进行分类的新兴工具。然而，现有的方法通常存在两个局限性：(1)它们每轮只聚合短距离（例如，1跳邻居）的信息，而不能捕获图中的长距离关系；(2)它们要求用户标记来自多个类别的数据，以方便判别模型的学习；而在现实中，用户可能只提供单个类中少量节点的标签。为了克服这些限制，本文提出了一种用于正无标记（PU）图学习的新型长短距离聚合网络（\ texttlsdan）。我们的主题是基于邻接矩阵生成不同距离的多个图，并进一步开发这些图的长短距离注意模型。短距离注意机制用于捕获邻居节点对目标节点的重要性。利用远程注意机制捕捉每个节点局部区域内的信息传播，帮助建立不同图的权重模型，进行节点表示学习。一个非负风险估计器被进一步用于聚合长短距离网络，用于使用反向传播损失模型进行PU学习。在真实世界数据集上的实验验证了我们方法的有效性。
Graph neural nets are emerging tools to represent network nodes for classification. However, existing approaches typically suffer from two limitations: (1) they only aggregate information from short distance (e.g., 1-hop neighbors) each round and fail to capturelong distance relationship in graphs; (2) they require users to label data from several classes to facilitate the learning of discriminative models; whereas in reality, users may only provide labels of a small number of nodes in a single class. To overcome these limitations, this paper presents a novel long-short distance aggregation networks (\textttLSDAN ) for positive unlabeled (PU) graph learning. Our theme is to generate multiple graphs at different distances based on the adjacency matrix, and further develop a long-short distance attention model for these graphs. The short-distance attention mechanism is used to capture the importance of neighbor nodes to a target node. The long-distance attention mechanism is used to capture the propagation of information within a localized area of each node and help model weights of different graphs for node representation learning. A non-negative risk estimator is further employed, to aggregate long- short-distance networks, for PU learning using back-propagated loss modeling. Experiments on real-world datasets validate the effectiveness of our approach.