预测图上的沉默多数：知识可迁移图神经网络
Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network
AI总结：
提出KT-GNN模型，通过特征补全、消息传递机制和基于KL散度的知识可迁移分类器，将发声节点知识迁移至沉默节点，有效解决VS-Graph上的分布偏移与缺失特征问题。
摘要：
由发声节点（“发声少数”）和沉默节点（“沉默多数”）组成的图，即VS-Graph，在现实世界中无处不在。发声节点往往具有丰富的特征和标签。相比之下，沉默节点只有不完整的特征和稀少的标签，例如在Twitter的社交网络上，政治家（发声）的描述和政治倾向很丰富，而普通人（沉默）则不然。预测沉默多数仍然是一个关键且具有挑战性的问题。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领域，没有考虑领域间的缺失特征和分布偏移，导致处理VS-Graph的能力较差。为了应对上述挑战，我们提出了知识可迁移图神经网络（KT-GNN），它通过将知识从发声节点迁移到沉默节点，在消息传递和表示学习过程中对分布偏移进行建模。具体来说，我们设计了领域自适应的“特征补全与消息传递机制”用于节点表示学习，同时保留领域差异。随后是一个基于KL散度的知识可迁移分类器。在真实世界场景（即公司财务风险评估和政治选举）上的综合实验证明了我们方法的优越性能。我们的源代码已经开源。
英文摘要：
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.
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。
