Joint embedding of structure and features via graph convolutional networks

  title={Joint embedding of structure and features via graph convolutional networks},
  author={S{\'e}bastien Lerique and Jacob Levy Abitbol and M. Karsai},
  journal={Applied Network Science},
  • Sébastien Lerique, Jacob Levy Abitbol, M. Karsai
  • Published 2020
  • Computer Science, Mathematics
  • Applied Network Science
  • The creation of social ties is largely determined by the entangled effects of people’s similarities in terms of individual characters and friends. However, feature and structural characters of people usually appear to be correlated, making it difficult to determine which has greater responsibility in the formation of the emergent network structure. We propose AN2VEC, a node embedding method which ultimately aims at disentangling the information shared by the structure of a network and the… CONTINUE READING
    Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
    • 9
    • PDF
    Computational Human Dynamics


    Publications referenced by this paper.
    Adam: A Method for Stochastic Optimization
    • 49,946
    • Highly Influential
    • PDF
    node2vec: Scalable Feature Learning for Networks
    • 3,315
    • PDF
    DeepWalk: online learning of social representations
    • 3,429
    • PDF
    Fast unfolding of communities in large networks
    • 9,763
    • PDF
    Semi-Supervised Classification with Graph Convolutional Networks
    • 4,680
    • Highly Influential
    • PDF
    The Strength of Weak Ties
    • 32,761
    • PDF
    Inductive Representation Learning on Large Graphs
    • 2,065
    • Highly Influential
    • PDF
    Community detection in graphs
    • 8,090
    • PDF
    Birds of a Feather: Homophily in Social Networks
    • 11,940
    • PDF
    Structural Deep Network Embedding
    • 1,086
    • Highly Influential
    • PDF