Graphs consisting of vocal nodes ("the vocal minority") and silent nodes ("the silent majority"), namely VS-Graph, are ubiquitous in the real world. The vocal nodes tend to have abundant features and labels. In contrast, silent nodes only have incomplete features and rare labels, e.g., the description and political tendency of politicians (vocal) are abundant while not for ordinary people (silent) on the twitter's social network. Predicting the silent majority remains a crucial yet challenging problem. However, most existing message-passing based GNNs assume that all nodes belong to the same domain, without considering the missing features and distribution-shift between domains, leading to poor ability to deal with VS-Graph. To combat the above challenges, we propose Knowledge Transferable Graph Neural Network (KT-GNN), which models distribution shifts during message passing and representation learning by transferring knowledge from vocal nodes to silent nodes. Specifically, we design the domain-adapted "feature completion and message passing mechanism" for node representation learning while preserving domain difference. And a knowledge transferable classifier based on KL-divergence is followed. Comprehensive experiments on real-world scenarios (i.e., company financial risk assessment and political elections) demonstrate the superior performance of our method. Our source code has been open sourced.
翻译:由包含有声节点(“发声的少数派”)和沉默节点(“沉默的大多数”)组成的图表,即VS-Graph,在现实世界中是普遍存在的。发声节点往往具有丰富的特征和标签。相反,沉默节点只有不完整的特征和少见的标签,例如推特社交网络上的政治家(发声)的描述和政治取向丰富,而普通人(沉默)则不然。预测沉默的大多数仍然是一项关键而具有挑战性的问题。然而,大多数现有的基于消息传递的GNN假设所有节点属于同一个领域,而不考虑不同领域之间的缺失特征和分布漂移,导致处理VS-Graph的能力较差。为了解决上述挑战,我们提出了可转移知识的图神经网络(KT-GNN),它通过从声音节点到沉默节点的知识转移来建模消息传递和表示学习过程中的分布漂移。具体而言,我们为节点表示学习设计了特定于域的“特征完成和消息传递机制”,同时保留领域差异。随后采用基于KL散度的可转移知识分类器。在现实世界的场景上(即公司财务风险评估和政治选举),我们的方法展示了卓越的性能。我们的源代码已经开源。