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 2103.04683cs.LG
收藏

具有正节点和未标记节点的学习图神经网络

Learning Graph Neural Networks with Positive and Unlabeled Nodes

Florida Atlantic University(佛罗里达大西洋大学);Monash University(莫纳什大学)

Man Wu, Shirui Pan, Lan Du, Xingquan Zhu

摘要:

图神经网络(GNN)是用于诸如图中的节点分类的传导学习任务的重要工具,这是由于它们在捕捉节点之间的复杂相互依赖性方面的表达能力。为了使图神经网络能够学习,现有的工作通常假设提供来自两个或多个类的标记节点,使得可以从标记数据中学习有区别的分类器。实际上,这种假设对于应用程序来说可能限制太多,因为用户可能只为少数节点提供单个类中感兴趣的标签。此外,大多数GNN模型仅聚合来自短距离的信息(例如,1-跳变邻居),且不能在图中捕获长距离关系。在本文中,我们提出了一种新的图神经网络框架,长短距离聚合网络(LSDAN),以克服这些限制。通过在不同距离水平上生成多个图,基于邻接矩阵,我们开发了一个长短距离注意模型来建模这些图。通过短距离注意力机制捕获直接邻居,并且通过长距离注意力机制捕获具有长距离的邻居。两个新的风险估计器进一步采用聚合长短距离网络,PU学习和模型学习的损失是反向传播。在真实数据集上的实验结果证明了该算法的有效性。

英文摘要:

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 graph neural network 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 paper, we propose a novel graph neural network framework, long-short distance aggregation networks (LSDAN), 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.

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。

↑