A Non-Negative Factorization approach to node pooling in Graph Convolutional Neural Networks

7 Sep 2019Davide BacciuLuigi Di Sotto

The paper discusses a pooling mechanism to induce subsampling in graph structured data and introduces it as a component of a graph convolutional neural network. The pooling mechanism builds on the Non-Negative Matrix Factorization (NMF) of a matrix representing node adjacency and node similarity as adaptively obtained through the vertices embedding learned by the model... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Graph Classification COLLAB 1-NMFPool Accuracy 65.0% # 25
Graph Classification D&D 1-NMFPool Accuracy 76.0% # 29
Graph Classification ENZYMES 1-NMFPool Accuracy 24.1% # 30
Graph Classification NCI1 1-NMFPool Accuracy 66.2% # 41
Graph Classification PROTEINS 1-NMFPool Accuracy 72.1% # 52

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet