Awesome GitHub RepositoriesNode Classification

DGL is a Python library for building and training graph neural networks. It functions as a graph message passing framework and a geometric deep learning tool, enabling the development of models that analyze graph-structured data. The library is designed for large-scale graph processing, utilizing distributed training and neighbor sampling to handle datasets with billions of edges. It provides specialized support for heterogeneous graph modeling, allowing for the representation of complex real-world entities with multiple node and edge types. Its capabilities cover a wide range of graph tasks

This is a graph convolutional network library designed for performing node and graph classification on graph-structured data. It functions as a framework for generating graph embeddings and implementing spectral convolutional neural networks to predict labels for nodes and entire graph structures. The library provides specialized tools for spectral graph convolutions, utilizing Chebyshev polynomial approximations to perform feature aggregation. It includes a multi-graph processing framework that manages batches of different graph instances through block-diagonal adjacency matrices and pooling

pygcn est une bibliothèque et un framework PyTorch pour implémenter des réseaux de neurones convolutifs sur graphes (GCN). Il fournit des outils pour la classification de nœuds semi-supervisée et la génération d'embeddings de nœuds à partir de données structurées en graphes. Le système convertit les nœuds de graphe en vecteurs de basse dimension basés sur des modèles de voisinage et des similarités locales. Il permet la prédiction des étiquettes de nœuds en tirant parti à la fois d'un petit ensemble d'exemples étiquetés et de la topologie globale du graphe. La bibliothèque couvre l'analyse de données relationnelles et l'apprentissage sur graphes semi-supervisé. Elle inclut des primitives de calcul pour le passage de messages, la transformation d'adjacence et la normalisation symétrique.

Memgraph is an in-memory, distributed graph database designed for high-performance labeled property graph management. It utilizes a Cypher query engine for declarative data retrieval and manipulation, providing a scalable knowledge graph backend that integrates vector search and graph traversals. The system distinguishes itself as a real-time graph analytics platform, employing native C++ and CUDA implementations to execute complex network analysis and dynamic community detection on streaming data. It provides specialized support for AI integration, including GraphRAG capabilities, the constr

GraphEmbedding is a graph network representation library and node embedding framework. It provides a toolkit for transforming complex network nodes into low-dimensional vector spaces, enabling the integration of relational graph data into machine learning workflows. The library functions as a dimensionality reduction toolkit and network topology analysis tool. It uses matrix-factorization techniques to preserve global connectivity and employs random-walk sampling with skip-gram based vector optimization to learn numerical representations of nodes. The framework covers several domain-specific

GraphSAGE is a graph neural network framework designed for inductive representation learning on large-scale graphs. It functions as an inductive graph embedding tool and neighborhood aggregation engine, enabling the generation of numerical node representations that generalize to previously unseen data. The system distinguishes itself by computing node embeddings through the aggregation of features from local neighborhoods rather than relying on a global lookup table. This approach allows the framework to operate as both a supervised graph classifier for predicting categorical node classes and

Graph Nets is a graph neural network library and educational toolkit implemented in PyTorch, providing implementations of popular graph representation learning algorithms and research papers. The project covers core graph machine learning tasks including semi-supervised node classification, inductive and unsupervised node embedding generation, and neighborhood feature aggregation. The library supports diverse algorithmic approaches for processing network structures, ranging from shared-parameter graph convolutions and attention-weighted neighborhood aggregation to spectral Chebyshev filtering

Ce dépôt sert de ressource éducative pour l'implémentation de réseaux de neurones sur graphes en utilisant Python. Il fournit une collection d'exemples de code structurés et de tutoriels conçus pour guider les développeurs à travers le processus de construction et d'entraînement de modèles de machine learning qui opèrent sur des jeux de données complexes et interconnectés. Le projet couvre les mécanismes fondamentaux de l'apprentissage profond sur graphes, y compris les architectures de passage de messages, l'agrégation de caractéristiques et l'empilement de couches convolutives. Il démontre comment représenter des données non euclidiennes sous forme de graphes statiques et comment gérer la mémoire pendant l'entraînement grâce à des techniques d'échantillonnage par mini-lots. Les implémentations incluses traitent des tâches analytiques courantes telles que la classification de nœuds, la prédiction de structure de graphe et l'intégration de sources de données hétérogènes dans des modèles unifiés. Le dépôt est organisé comme une série d'exercices pratiques qui traduisent les concepts théoriques de graphes en flux de travail de machine learning fonctionnels.