With the development of various applications, such as social networks and knowledge graphs, graph data has been ubiquitous in the real world. Unfortunately, graphs usually suffer from being absent due to privacy-protecting policies or copyright restrictions during data collection. The absence of graph data can be roughly categorized into attribute-incomplete and attribute-missing circumstances. Specifically, attribute-incomplete indicates that a part of the attribute vectors of all nodes are incomplete, while attribute-missing indicates that the whole attribute vectors of partial nodes are missing. Although many efforts have been devoted, none of them is custom-designed for a common situation where both types of graph data absence exist simultaneously. To fill this gap, we develop a novel network termed Revisiting Initializing Then Refining (RITR), where we complete both attribute-incomplete and attribute-missing samples under the guidance of a novel initializing-then-refining imputation criterion. Specifically, to complete attribute-incomplete samples, we first initialize the incomplete attributes using Gaussian noise before network learning, and then introduce a structure-attribute consistency constraint to refine incomplete values by approximating a structure-attribute correlation matrix to a high-order structural matrix. To complete attribute-missing samples, we first adopt structure embeddings of attribute-missing samples as the embedding initialization, and then refine these initial values by adaptively aggregating the reliable information of attribute-incomplete samples according to a dynamic affinity structure. To the best of our knowledge, this newly designed method is the first unsupervised framework dedicated to handling hybrid-absent graphs. Extensive experiments on four datasets have verified that our methods consistently outperform existing state-of-the-art competitors.
翻译:随着社交网络和知识图表等各种应用的开发,图形数据在现实世界中无处不在。 不幸的是,图表通常因缺乏隐私保护政策或数据收集过程中的版权限制而缺乏。 没有图形数据可以大致分为属性不完整和属性缺失的情况。 具体地说, 属性不完整表明, 所有节点的一部分属性矢量不完整, 而属性缺失则表明, 部分节点的全部属性矢量缺失。 尽管已经做出了许多努力, 但其中没有一个是针对两种类型图形数据同时存在的共同情况定制的。 为了填补这一空白,我们开发了一个名为“ 重新审视“ 初始初始初始初始初始初始” 的网络。 在创新初始初始初始初始“ 初始” 优化“ 初始” 初始“ 初始” 初始“ 初始 初始” 的图形。 在新初始初始初始“ 初始” 初始化” 之前,我们根据初始初始初始初始初始“ 初始” 初始” 的属性矢量矢量矢量, 将当前“ 更新” 初始“ 初始” 结构“ 结构” 初始“ 结构” 引入“ 初始” 结构“初始” 结构 结构 。 将“ 最新” 更新“ 高级” 的“当前” 的“当前”, 的“当前”, 的“当前” 的“当前” 构建”, 的“当前” 的“结构” 将“结构” 引入”,, 的“当前” 的“当前” 的“当前” 的“当前“结构” 的“结构” 的” 的“结构”,将“结构” 的“当前”, 引入“当前” 的“当前” 的“结构” 的“结构”,,,, 的“结构,,,将“结构”,将“结构” 的”,通过” 的” 的”,通过“当前“当前“当前“结构” 的“结构“结构” 的“结构”,通过” 的“结构”,通过” 的” 的” 的” 的”,通过一个“当前”,通过一个“当前“当前” 的”,通过“结构”,通过” 的”