Learning Graph Neural Networks with Positive and Unlabeled Nodes
Learning Graph Neural Networks with Positive and Unlabeled Nodes
复制标题
DOI：
10.1145/3450316
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Man Wu;Shirui Pan;Lan Du;Xingquan Zhu
中科院分区：
文献类型：
--
作者：
Man Wu;Shirui Pan;Lan Du;Xingquan Zhu
图神经网络（GNNs）是转导学习任务（例如图中的节点分类）的重要工具，因为它们在捕捉节点之间复杂的相互依赖关系方面具有表达能力。为了实现GNN学习，现有的工作通常假设提供了来自两个或多个类别的标记节点，以便可以从标记数据中学习到一个判别分类器。在实际应用中，这一假设可能限制过多，因为用户可能只对少量节点提供单一类别的感兴趣标签。此外，大多数GNN模型在每一轮中仅聚合短距离（例如，1跳邻居）的信息，无法捕捉图中的长距离关系。在本文中，我们提出了一种新颖的GNN框架——长短距离聚合网络，以克服这些限制。通过基于邻接矩阵在不同距离级别生成多个图，我们开发了一个长短距离注意力模型来对这些图进行建模。直接邻居通过短距离注意力机制被捕捉，长距离邻居则通过长距离注意力机制被捕捉。我们进一步采用了两种新颖的风险估计器来聚合长短距离网络，用于正未标记（PU）学习，并通过反向传播损失来进行模型学习。在真实数据集上的实验结果证明了我们算法的有效性。
Graph neural networks (GNNs) are important tools for transductive learning tasks, such as node classification in graphs, due to their expressive power in capturing complex interdependency between nodes. To enable GNN learning, existing works typically assume that labeled nodes, from two or multiple classes, are provided, so that a discriminative classifier can be learned from the labeled data. In reality, this assumption might be too restrictive for applications, as users may only provide labels of interest in a single class for a small number of nodes. In addition, most GNN models only aggregate information from short distances (e.g., 1-hop neighbors) in each round, and fail to capture long-distance relationship in graphs. In this article, we propose a novel GNN framework, long-short distance aggregation networks, to overcome these limitations. By generating multiple graphs at different distance levels, based on the adjacency matrix, we develop a long-short distance attention model to model these graphs. The direct neighbors are captured via a short-distance attention mechanism, and neighbors with long distance are captured by a long-distance attention mechanism. Two novel risk estimators are further employed to aggregate long-short-distance networks, for PU learning and the loss is back-propagated for model learning. Experimental results on real-world datasets demonstrate the effectiveness of our algorithm.