Graph Representation Learning
Graphic Mutual Information
Introduced by Peng et al. in Graph Representation Learning via Graphical Mutual Information MaximizationGraphic Mutual Information, or GMI, measures the correlation between input graphs and high-level hidden representations. GMI generalizes the idea of conventional mutual information computations from vector space to the graph domain where measuring mutual information from two aspects of node features and topological structure is indispensable. GMI exhibits several benefits: First, it is invariant to the isomorphic transformation of input graphs---an inevitable constraint in many existing graph representation learning algorithms; Besides, it can be efficiently estimated and maximized by current mutual information estimation methods such as MINE.
Source: Graph Representation Learning via Graphical Mutual Information Maximization
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Registration | 1 | 16.67% |
| Medical Image Registration | 1 | 16.67% |
| Graph Representation Learning | 1 | 16.67% |
| Link Prediction | 1 | 16.67% |
| Mutual Information Estimation | 1 | 16.67% |
| Node Classification | 1 | 16.67% |
1x1 Convolution
