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 2106.12839cs.LGcs.HC
收藏

用CorGIE可视化图神经网络:将图与其嵌入相对应

Visualizing Graph Neural Networks with CorGIE: Corresponding a Graph to Its Embedding

University of British Columbia(不列颠哥伦比亚大学);Facebook Inc.(Facebook公司)

Zipeng Liu, Yang Wang, Jürgen Bernard, Tamara Munzner

AI总结:

本文提出CorGIE交互式可视化界面,通过K-hop图布局将输入图与其节点嵌入相对应,帮助GNN开发者理解模型是否真正学到图的特征,并通过案例研究验证其功能性与可用性。

摘要:

图神经网络(GNNs)是一类强大的机器学习工具,通过对节点关系建模来预测节点或链接。GNN开发者依赖预测的定量指标来评估GNN,但与许多其他神经网络类似,他们很难理解GNN是否真正如预期那样学习到了图的特征。我们提出一种将输入图与其节点嵌入(即潜在空间)相对应的方法,节点嵌入是GNN中后续用于预测的常见组件。我们对数据和任务进行抽象,并开发了一个名为CorGIE的交互式多视图界面来实例化该抽象。作为CorGIE的关键功能,我们提出了K-hop图布局,用于展示拓扑邻居的跳数及其聚类结构。为了评估CorGIE的功能性和可用性,我们展示了如何在两个使用场景中使用CorGIE,并与五位GNN专家进行了一项案例研究。

英文摘要:

Graph neural networks (GNNs) are a class of powerful machine learning tools that model node relations for making predictions of nodes or links. GNN developers rely on quantitative metrics of the predictions to evaluate a GNN, but similar to many other neural networks, it is difficult for them to understand if the GNN truly learns characteristics of a graph as expected. We propose an approach to corresponding an input graph to its node embedding (aka latent space), a common component of GNNs that is later used for prediction. We abstract the data and tasks, and develop an interactive multi-view interface called CorGIE to instantiate the abstraction. As the key function in CorGIE, we propose the K-hop graph layout to show topological neighbors in hops and their clustering structure. To evaluate the functionality and usability of CorGIE, we present how to use CorGIE in two usage scenarios, and conduct a case study with five GNN experts.

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。

↑