pygmtools.neural_solvers
Neural networkbased graph matching solvers. It is recommended to integrate these networks as modules into your existing deep learning pipeline (either supervised, unsupervised or reinforcement learning).
Functions
The CIE (Channel Independent Embedding) graph matching neural network model for processing two individual graphs (KBQAP). 

The GENNA* (Graph Edit Neural Network A*) solver for graph matching (and graph edit distance) based on the fusion of traditional A* and Neural Network. 

The IPCAGM (Iterative Permutation loss and Crossgraph Affinity Graph Matching) neural network model for processing two individual graphs (KBQAP). 

The NGM (Neural Graph Matching) model for processing the affinity matrix (the most general form of Lawler's QAP). 

The PCAGM (Permutation loss and Crossgraph Affinity Graph Matching) neural network model for processing two individual graphs (KBQAP). 