CONE-Align: Consistent Network Alignment with Proximity-Preserving Node Embedding

Abstract

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.

In Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM), 2020

References in corpus (8)

• DeepWalk: Online Learning of Social Representations
• Graph Embedding Techniques, Applications, and Performance: A Survey
• struc2vec: Learning Node Representations from Structural Identity
• Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
• REGAL: Representation Learning-based Graph Alignment
• Unsupervised Alignment of Embeddings with Wasserstein Procrustes
• LazySVD: Even Faster SVD Decomposition Yet Without Agonizing Pain
• Massively scalable Sinkhorn distances via the Nyström method

Cited by in corpus (2)

• Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors
• CAPER: Coarsen, Align, Project, Refine - A General Multilevel Framework for Network Alignment