English

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

Social and Information Networks 2020-08-19 v2 Machine Learning

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.

Keywords

Cite

@article{arxiv.2005.04725,
  title  = {CONE-Align: Consistent Network Alignment with Proximity-Preserving Node Embedding},
  author = {Xiyuan Chen and Mark Heimann and Fatemeh Vahedian and Danai Koutra},
  journal= {arXiv preprint arXiv:2005.04725},
  year   = {2020}
}

Comments

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