CONE-Align: Consistent Network Alignment with Proximity-Preserving Node Embedding
This addresses network alignment for scientific and industrial applications, offering a robust solution with significant accuracy improvements in noisy conditions.
The paper tackled the problem of suboptimal unsupervised network alignment that breaks up node neighborhoods by proposing CONE-Align, which uses node embeddings to preserve proximity and achieved 19.25% greater accuracy on average than the best state-of-the-art method in noisy settings.
Network alignment, the process of finding correspondences between nodes in different graphs, has many scientific and industrial applications. Existing unsupervised network alignment methods find suboptimal alignments that break up node neighborhoods, i.e. do not preserve matched neighborhood consistency. To improve this, we propose CONE-Align, which models intra-network proximity with node embeddings and uses them to match nodes across networks after aligning the embedding subspaces. Experiments on diverse, challenging datasets show that CONE-Align is robust and obtains 19.25% greater accuracy on average than the best-performing state-of-the-art graph alignment algorithm in highly noisy settings.