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 2012.08698cs.LGeess.SP
收藏

边缘熵作为GNNs对CNN节点分类有效性的指标

Edge Entropy as an Indicator of the Effectiveness of GNNs over CNNs for Node Classification

Carnegie Mellon University(卡内基梅隆大学)

Lavender Yao Jiang, John Shi, Mark Cheung, Oren Wright, José M. F. Moura

摘要:

图神经网络(GNN)将卷积神经网络(CNN)扩展到基于图的数据。出现的一个问题是GNN中的底层图结构相对于CNN(忽略此图结构)提供了多少性能改进。为了解决这个问题,我们引入了边缘熵,并评估了它对GNN相对于CNN的性能改进的可能性。我们对合成数据集和真实数据集的节点分类结果表明,较低的边缘熵值预测GNN相对于CNN的预期性能增益较大,相反,较高的边缘熵导致预期较小的改进增益。

英文摘要:

Graph neural networks (GNNs) extend convolutional neural networks (CNNs) to graph-based data. A question that arises is how much performance improvement does the underlying graph structure in the GNN provide over the CNN (that ignores this graph structure). To address this question, we introduce edge entropy and evaluate how good an indicator it is for possible performance improvement of GNNs over CNNs. Our results on node classification with synthetic and real datasets show that lower values of edge entropy predict larger expected performance gains of GNNs over CNNs, and, conversely, higher edge entropy leads to expected smaller improvement gains.

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。

↑