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
Source: Hierarchical Graph Representation Learning with Differentiable PoolingPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Graph Classification | 3 | 20.00% |
General Classification | 2 | 13.33% |
Active Learning | 1 | 6.67% |
Molecular Property Prediction | 1 | 6.67% |
Property Prediction | 1 | 6.67% |
Time Series Analysis | 1 | 6.67% |
Graph Attention | 1 | 6.67% |
graph partitioning | 1 | 6.67% |
Classification | 1 | 6.67% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |