Hybrid Node Embeddings of Homegenoius Graph/Network Using Both Conventioanl and Representative Learning Techniques

These Node embeddings Generated are used as Feature Maps in various Downstream Tasks like Node Classification, Link Prediction, Recommnedation System, Community Detection, Clustering etc.. .

Folder Structure:

Clustering Graph Clustering using Knn, Laplacian Normalisation Eigen maps,Modularity Clustering and Non NFMV
gm_Project Hybrid Node Embedding System Using Spectral Clustring, HOPE and Node2Vec. Includes both Random walk based representation Learning and Matrix Factorization Based
gm_Project/data Consists of two types of Graph data

Infrastructure:

Python 3.6
Networkx
Stellargraph
GEM
Gensim
Jupyternotebooks
Miniconda(used to create virtual envinorments).
"requirments.txt" Consists of all other dependices required for virtual evinorment set-up