Generalizing Weisfeiler-Lehman Kernels to Subgraphs
Dongkwan Kim, Alice Oh
Subgraph表示学习在解决各种现实问题方面是有效的。 然而,当前的图神经网络(GNN)由于无法捕获子图内部和子图之间的复杂相互作用,为子图级任务产生次优结果。 为了提供更具表现力和更有效的替代方案,我们提出了WLKS,一个Weisfeiler-Lehman(WL)内核,通过在诱导的k-hop社区上应用WL算法,为子图进行广义。 我们在不同的 k-hop 级别上组合内核,以捕获在现有模型中未完全编码的更丰富的结构信息。 我们的方法可以通过消除邻里采样的需要来平衡表现力和效率。 在8个真实世界和合成基准的实验中,WLKS在五个数据集上明显优于领先方法,同时减少了训练时间,与最先进的数据相比,从0.01倍到0.25倍不等。
Subgraph representation learning has been effective in solving various real-world problems. However, current graph neural networks (GNNs) produce suboptimal results for subgraph-level tasks due to their inability to capture complex interactions within and between subgraphs. To provide a more expressive and efficient alternative, we propose WLKS, a Weisfeiler-Lehman (WL) kernel generalized for subgraphs by applying the WL algorithm on induced k-hop neighborhoods. We combine kernels across differe...