REGAL: Representation Learning-based Graph Alignment

@inproceedings{Heimann2018REGALRL,
  title={REGAL: Representation Learning-based Graph Alignment},
  author={Mark Heimann and Haoming Shen and Tara Safavi and Danai Koutra},
  booktitle={CIKM},
  year={2018}
}
Problems involving multiple networks are prevalent in many scientific and other domains. In particular, network alignment, or the task of identifying corresponding nodes in different networks, has applications across the social and natural sciences. Motivated by recent advancements in node representation learning for single-graph tasks, we propose REGAL (REpresentation learning-based Graph ALignment), a framework that leverages the power of automatically-learned node representations to match… CONTINUE READING
4
Twitter Mentions

Similar Papers

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • REGAL runs up to 30x faster in the representation learning stage than comparable methods, outperforms existing network alignment methods by 20 to 30% accuracy on average, and scales to networks with millions of nodes each.
  • Experiments on real graphs show that xNetMF runs up to 30× faster than several existing network embedding techniques, and REGAL outperforms traditional network alignment methods by 20-30% in accuracy.

Citations

Publications citing this paper.
SHOWING 1-10 OF 10 CITATIONS

Cross-Network Embedding for Multi-Network Alignment

  • WWW
  • 2019
VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Deep Adversarial Network Alignment

VIEW 14 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Bridging Network Embedding and Graph Summarization

  • ArXiv
  • 2018
VIEW 3 EXCERPTS
CITES BACKGROUND