struc2vec: Learning Node Representations from Structural Identity

@article{Ribeiro2017struc2vecLN,
  title={struc2vec: Learning Node Representations from Structural Identity},
  author={Leonardo Filipe Rodrigues Ribeiro and Pedro H. P. Saverese and Daniel R. Figueiredo},
  journal={ArXiv},
  year={2017},
  volume={abs/1704.03165}
}
  • Leonardo Filipe Rodrigues Ribeiro, Pedro H. P. Saverese, Daniel R. Figueiredo
  • Published in KDD '17 2017
  • Computer Science, Mathematics
  • Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been addressed with representational learning techniques. This work presents struc2vec, a novel and flexible framework for learning latent representations for the structural identity of nodes. struc2vec uses a hierarchy to measure… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 243 CITATIONS

    Cross-domain network representations

    VIEW 14 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Hyperbolic Function Embedding: Learning Hierarchical Representation for Functions of Source Code in Hyperbolic Space

    VIEW 11 EXCERPTS
    CITES RESULTS & METHODS
    HIGHLY INFLUENCED

    RiWalk: Fast Structural Node Embedding via Role Identification

    VIEW 17 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Tutorial on NLP-Inspired Network Embedding

    VIEW 5 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    EpiRep: Learning Node Representations through Epidemic Dynamics on Networks

    VIEW 4 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    From Community to Role-based Graph Embeddings

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    MMNR: A Network Representation Framework Based on Multi-View Motif Fusion

    • Jingjing Xu, Ai-min Yu, Lijun Cai, Dan Meng
    • 2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom)
    • 2019
    VIEW 5 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    MrMine: Multi-resolution Multi-network Embedding

    VIEW 11 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2016
    2020

    CITATION STATISTICS

    • 42 Highly Influenced Citations

    • Averaged 75 Citations per year from 2017 through 2019

    • 56% Increase in citations per year in 2019 over 2018

    References

    Publications referenced by this paper.
    SHOWING 1-4 OF 4 REFERENCES

    RolX: structural role extraction & mining in large graphs

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    node2vec: Scalable Feature Learning for Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    DeepWalk: online learning of social representations

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL