parcellearning
This is a python package to apply various graph neural network models to brain connectivity data to learn cortical brain maps. These models address the issue of node classification, as commonly seen in the graph representation learning community. These models are based on the Deep Graph Library.
Current models include the following:
Posts
Jumping-Knowledge Representation Learning With LSTMs
Background As I mentioned in my previous post on constrained graph attention networks, graph neural networks suffer from overfitting and oversmoothing as network depth increases. These issues can ultimately be linked to the local topologies of the graph.
Constrained Graph Attention Networks
In their recent paper, Wang et al. propose a few updates to the Graph Attention Network (GAT) neural network algorithm (if you want to skip the technical bit and get to the code, click here). Briefly, GATs are a recently-developed neural network architecture applied to data distributed over a graph domain.
Gaussian Graph Convolutional Networks
I’m using graph convolutional networks as a tool to segment the cortical surface of the brain. This research resides in the domain of node classification using inductive learning. By node classification, I mean that we wish to assign a discrete label to cortical surface locations (nodes / vertices in a graph) on the basis of some feature data and brain network topology.