CoRGi:具有注意力的内容丰富的图神经网络
CoRGi: Content-Rich Graph Neural Networks with Attention
摘要:
目标域的图形表示通常将其投影到一组实体(节点)及其关系(边)。然而,这样的预测往往错过重要和丰富的信息。例如,在缺失值填补中使用的图形表示中,表示为节点的项可能包含丰富的文本信息。然而,当用图神经网络(GNN)处理图时,这样的信息要么被忽略,要么被汇总到用于初始化GNN的单个向量表示中。为了解决这个问题,我们提出了CoRGi,这是一个GNN,它在邻居的上下文中考虑节点内的丰富数据。这是通过在每个节点的内容上赋予CoRGi的消息传递以个性化的注意力机制来实现的。通过这种方式,CoRGi会根据出现在项目内容中的单词来分配特定于用户项目的注意力分数。我们在两个边缘值预测任务上评估了CoRGi,并表明CoRGi在现有方法的边缘值预测方面更好,特别是在图的稀疏区域上。
英文摘要:
Graph representations of a target domain often project it to a set of entities (nodes) and their relations (edges). However, such projections often miss important and rich information. For example, in graph representations used in missing value imputation, items - represented as nodes - may contain rich textual information. However, when processing graphs with graph neural networks (GNN), such information is either ignored or summarized into a single vector representation used to initialize the GNN. Towards addressing this, we present CoRGi, a GNN that considers the rich data within nodes in the context of their neighbors. This is achieved by endowing CoRGi's message passing with a personalized attention mechanism over the content of each node. This way, CoRGi assigns user-item-specific attention scores with respect to the words that appear in an item's content. We evaluate CoRGi on two edge-value prediction tasks and show that CoRGi is better at making edge-value predictions over existing methods, especially on sparse regions of the graph.
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。