Node Classification in Heterogeneous Graphs Using PyG and SBERT SentenceTransformers
Discover AI via YouTube
Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Learn to implement node classification on heterogeneous graphs using PyTorch Geometric (PyG) and SBERT Sentence Transformers in this 42-minute tutorial. Explore real-world applications of graph-structured data including social networks, cybersecurity systems, and molecular representations through hands-on coding in a free Google Colab notebook. Master essential concepts of heterogeneous graphs, which contain different types of entities and relationships, and understand how to map node and edge information into PyG's data structures. Gain practical experience with machine learning models like Node2Vec, Message Passing Neural Networks (MP-GNN), and Graph Convolutional Networks (GCN) for tasks such as fraud detection in cybersecurity networks. Discover how to transform heterogeneous graph data into suitable inputs for Graph Neural Network models, with a special focus on recommendation systems and social graph applications.
Syllabus
PyG + SBERT: Heterogeneous Graphs Using SBERT SentenceTransformers for Node Classification SBERT 46
Taught by
Discover AI