Data Science Advanced Seminar "Incomplete Network Imbedding"
-
Updated
Sep 1, 2020 - Python
Data Science Advanced Seminar "Incomplete Network Imbedding"
This notebook is part of a project on Graph Embedding Techniques. It's a comparison between DeepWalk and Node2Vec using SkipGram applied to a dataset called Github Social Network. I did several tests with different p and q values for Node2Vec, the last p = 0.25 and q = 0.25 were the ones that gave me the best result.
Zero-to-hero for Graph Neural Networks
Implementations of different NLP tasks
Inverstigate different graph embedding algorithms
Tensorflow implementation of HARP (https://research.google.com/pubs/pub46519.html)
My implementation of Deepwalk in PyTorch
Implementing deep learning models from an under the hood perspective.
GitHub repository vulnerability detection and metrics.
A newly interpreted code of C++ project `SMORe`, which developed in Python to enhance the usage-flexibility and migration-potential.
PyTorch implementation of Splitter graph node embeddings
Deepwalk implements graph embedding, and uses k-means for clustering based on the embedding results.
Torch geometric compatible node embedders
Benchmarking Node2vec and DeepWalk for course on Graph Neural Networks
Add a description, image, and links to the deepwalk topic page so that developers can more easily learn about it.
To associate your repository with the deepwalk topic, visit your repo's landing page and select "manage topics."