Corpus ID: 3290366

Graph Partition Neural Networks for Semi-Supervised Classification

  title={Graph Partition Neural Networks for Semi-Supervised Classification},
  author={Renjie Liao and Marc Brockschmidt and Daniel Tarlow and Alexander L. Gaunt and R. Urtasun and R. Zemel},
  • Renjie Liao, Marc Brockschmidt, +3 authors R. Zemel
  • Published 2018
  • Computer Science, Mathematics
  • ArXiv
  • We present graph partition neural networks (GPNN), an extension of graph neural networks (GNNs) able to handle extremely large graphs. GPNNs alternate between locally propagating information between nodes in small subgraphs and globally propagating information between the subgraphs. To efficiently partition graphs, we experiment with several partitioning algorithms and also propose a novel variant for fast processing of large scale graphs. We extensively test our model on a variety of semi… CONTINUE READING
    33 Citations
    Hop-Hop Relation-aware Graph Neural Networks
    • PDF
    Hierarchical Graph Representation Learning with Differentiable Pooling
    • 533
    • PDF
    Confidence-based Graph Convolutional Networks for Semi-Supervised Learning
    • 15
    • Highly Influenced
    • PDF
    Label Efficient Semi-Supervised Learning via Graph Filtering
    • 36
    • PDF
    Lovasz Convolutional Networks
    • 6
    • PDF
    Computing Graph Neural Networks: A Survey from Algorithms to Accelerators
    • 1
    • PDF
    Generalized Label Propagation Methods for Semi-Supervised Learning
    • 1
    Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning
    • 3
    • PDF


    Semi-Supervised Classification with Graph Convolutional Networks
    • 5,667
    • Highly Influential
    • PDF
    A new model for learning in graph domains
    • 530
    Gated Graph Sequence Neural Networks
    • 1,239
    • PDF
    Inductive Representation Learning on Large Graphs
    • 2,518
    • PDF
    node2vec: Scalable Feature Learning for Networks
    • 3,787
    • PDF
    The Graph Neural Network Model
    • 1,747
    • PDF
    Revisiting Semi-Supervised Learning with Graph Embeddings
    • 687
    • Highly Influential
    • PDF
    Spectral Networks and Locally Connected Networks on Graphs
    • 1,820
    • PDF
    Few-Shot Learning with Graph Neural Networks
    • 392
    • PDF
    Collective Classification in Network Data
    • 1,425
    • Highly Influential