链式2-FWL图神经网络用于组合图对齐
Chaining 2-FWL GNNs for Combinatorial Graph Alignment
AI总结:
针对组合图对齐问题,提出链式2-FWL GNN方法,通过非可微排序注入离散反馈,在稀疏随机图和正则图上显著优于FAQ和现有GNN方法。
摘要:
对于组合图对齐问题(GAP)——寻找最大化两个无标签图之间公共边数(nce)的节点对应关系——适当初始化的FAQ仍然是强大的经典基线,而现有的GNN方法在纯结构设置中表现不佳。我们引入了一种链式过程:一系列Folklore类型(2-FWL)的GNN,其中每个网络在解码前一个网络的相似性矩阵并根据当前对齐质量对节点进行排序后,使用交叉熵进行训练。这个不可微的排序步骤在每个链接处注入离散的组合反馈;在推理时,我们迭代最终网络并保留具有最高观测nce的候选。在噪声水平0.25的稀疏Erdos-Renyi图上,带有FAQ后处理的链式FGNN达到85%的准确率,而FAQ从凸松弛初始化仅为13%,先前的GNN方法基本为0%。在相关正则图上,其中具有恒定特征的MPNN产生相同的节点嵌入(1-WL无法细化)且FAQ的凸初始化退化,链式是我们知道的唯一能够恢复非平凡对齐的方法。在三个真实世界基准(酵母PPI、合著和道路网络)上,我们表明最近的比较通过从均匀双随机矩阵初始化FAQ低估了FAQ;一旦FAQ从凸松弛初始化,它已经超过了先前报告的数字,而数据集特定的链式FGNN进一步改进了这个加强的基线。
英文摘要:
For the combinatorial graph alignment problem (GAP), finding the node correspondence that maximizes the number of common edges (nce) between two unlabeled graphs, the classical Frank-Wolfe heuristic FAQ remains a strong baseline once it is properly initialized, while existing GNN approaches struggle in the purely structural setting. We introduce a chaining procedure: a sequence of Folklore-type (2-FWL) GNNs in which each network is trained with cross-entropy after decoding the previous network's similarity matrix and ranking nodes by their current alignment quality. This non-differentiable ranking step injects discrete combinatorial feedback at every stage; at inference, we iterate the final network and keep the candidate with highest observed nce. On sparse Erdos-Renyi graphs at noise level 0.25, chained FGNNs used to initialize FAQ reach 85% accuracy versus 13% for FAQ initialized from the convex relaxation, and essentially 0% for prior GNN methods. On correlated regular graphs, where MPNNs with constant features produce identical node embeddings (1-WL fails to refine) and FAQ's convex initialization is degenerate, chaining is the only method among those we evaluate, including Gromov-Wasserstein solvers, that recovers a non-trivial alignment. On three real-world benchmarks (yeast PPI, coauthorship, and road networks), recent comparisons underestimate FAQ by initializing it from a uniform doubly stochastic matrix; initialized from the convex relaxation it already surpasses prior reported numbers, and dataset-specific chained FGNNs further improve on this strengthened baseline. Code and pretrained chains available at: https://github.com/mlelarge/chaining-gnn-graph-alignment.
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。