Description
DiffPool is a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion. DiffPool learns a differentiable soft cluster assignment for nodes at each layer of a deep GNN, mapping nodes to a set of clusters, which then form the coarsened input for the next GNN layer.
Description and image from: Hierarchical Graph Representation Learning with Differentiable Pooling
Papers Using This Method
Tackling Oversmoothing in GNN via Graph Sparsification: A Truss-based Approach2024-07-16On Graph Neural Network Ensembles for Large-Scale Molecular Property Prediction2021-06-29Adaptive Visibility Graph Neural Network and It's Application in Modulation Classification2021-06-16GNNIE: GNN Inference Engine with Load-balancing and Graph-Specific Caching2021-05-21SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features2020-06-03Pooling in Graph Convolutional Neural Networks2020-04-07Hierarchical Graph Representation Learning with Differentiable Pooling2018-06-22