node-classification-methods-analysis

Part of master's degree.

Worked on analyisis of node classification techniques in graph machine learning. Tested on various datasets Node2Vec, GraphSAGE, GCN and GAT.

Here are some of the results:

  • GAT accuracy 82.1% on CORA dataset - visualized with tSNE method:

  • GCN accuracy of 76% on CORA dataset - visualized with tSNE method:

  • Node2Vec accuracy of 73% on CORA - visualized with tSNE method: