Make GNN easy to start with
-
Updated
Jul 28, 2024 - Jupyter Notebook
Make GNN easy to start with
Graph Search based on Embedding Similarity
Developed a specialized RandomWalk algorithm for bipartite graphs on an ingredient dataset to replace allergenic ingredients while maintaining the nutritional value of the dish, and clustered them into 10 main clusters with 6 of them being highly specific.
It is a simple machine learning algorithm to get the latent vector of the Molecules from the datasets. After that we address the imbalance problem in the dataset and handle it by using various resampling techniques. Then we measure the performance of the algorithm by deploying various Classifiers.
面向大连理工大学学者,基于大连理工大学机构知识库,推荐潜在主题词,优化科研方向,促进跨学部、学科、领域科研合作。
Reimplementation of Graph Embedding methods by Pytorch.
Persona2vec: A Flexible Multi-role Representations Learning Framework for Graphs
Ulya Bayram, Runia Roy, Aqil Assalil, Lamia Ben Hiba, "The Unknown Knowns: A Graph-Based Approach for Temporal COVID-19 Literature Mining", Online Information Review (OIR), COVID-19 Special Issue, 2021.
Explained Graph Embedding generation and link prediction
Python Graph Embedding Library for Knowledge graph
graph embedding spark implementation, include deepWalk, Node2Vec etc
Add a description, image, and links to the graphembedding topic page so that developers can more easily learn about it.
To associate your repository with the graphembedding topic, visit your repo's landing page and select "manage topics."