MinCutPool is a trainable pooling operator for graphs that learns to map nodes into clusters. The method is trained to approximate the minimum K-cut of the graph to ensure that the clusters are balanced, while also jointly optimizing the objective of the task at hand.
Source: Spectral Clustering with Graph Neural Networks for Graph PoolingPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Clustering | 1 | 25.00% |
Graph Classification | 1 | 25.00% |
Graph Clustering | 1 | 25.00% |
Semantic Segmentation | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |