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 2402.05934cs.LGcs.SI
收藏

无需GNN的图节点分类

Classifying Nodes in Graphs without GNNs

The Hebrew University of Jerusalem(耶路撒冷希伯来大学)

Daniel Winter, Niv Cohen, Yedid Hoshen

AI总结:

本文提出一种完全无需GNN的节点分类方法,通过平滑约束、伪标签迭代和邻域标签直方图,在引文和共购买网络上达到与最先进GNN相当的准确率。

摘要:

图神经网络(GNNs)是图节点分类的主导范式,但其消息传递架构导致若干不良属性。近期,蒸馏方法成功消除了测试时对GNN的使用,但训练时仍需它们。我们对GNN在蒸馏方法中所扮演的角色进行了仔细分析。该分析促使我们提出一种完全无GNN的节点分类方法,在训练和测试时均不需要GNN。我们的方法包含三个关键组件:平滑性约束、伪标签迭代和邻域标签直方图。我们的最终方法在标准流行基准(如引文网络和共购买网络)上可以达到最先进的准确率,而无需训练GNN。

英文摘要:

Graph neural networks (GNNs) are the dominant paradigm for classifying nodes in a graph, but they have several undesirable attributes stemming from their message passing architecture. Recently, distillation methods succeeded in eliminating the use of GNNs at test time but they still require them during training. We perform a careful analysis of the role that GNNs play in distillation methods. This analysis leads us to propose a fully GNN-free approach for node classification, not requiring them at train or test time. Our method consists of three key components: smoothness constraints, pseudo-labeling iterations and neighborhood-label histograms. Our final approach can match the state-of-the-art accuracy on standard popular benchmarks such as citation and co-purchase networks, without training a GNN.

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。

↑