arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.06857cs.LG
收藏

图神经网络应该使用特征、边还是两者兼而有之?

Should Graph Neural Networks Use Features, Edges, Or Both?

ETH Zurich(苏黎世联邦理工学院)

Lukas Faber, Yifan Lu, Roger Wattenhofer

摘要:

图神经网络(GNNs)是图数据学习算法的首选。GNN承诺在端到端学习算法中集成(i)节点特征以及(ii)边缘信息。这个承诺实际上是如何实现的?在本文中,我们研究了如何扩展GNNs来解决突出的图分类问题。我们发现,对于图分类,GNN不超过其部分的总和。我们还发现,与特征不同,仅边缘模型的预测并不总是转移到GNN。

英文摘要:

Graph Neural Networks (GNNs) are the first choice for learning algorithms on graph data. GNNs promise to integrate (i) node features as well as (ii) edge information in an end-to-end learning algorithm. How does this promise work out practically? In this paper, we study to what extend GNNs are necessary to solve prominent graph classification problems. We find that for graph classification, a GNN is not more than the sum of its parts. We also find that, unlike features, predictions with an edge-only model do not always transfer to GNNs.

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。

↑