Node embedding frameworks
For node embedding frameworks, the strongest matches are rusty1s/pytorch_geometric (PyTorch Geometric is the flagship Python and PyTorch-based framework), williamleif/graphsage (GraphSAGE is a Python framework built for inductive representation) and dmlc/dgl (This repository provides a comprehensive graph neural network framework). pyg-team/pytorch_geometric and tkipf/pygcn round out the shortlist. Each is ranked by relevance to your query, popularity and recent activity.
Compare the top open-source node embedding frameworks for graph machine learning, ranked by GitHub stars and activity to find your best fit.
Node embedding frameworks
Find the best repos with AI.We'll search the best matching repositories with AI.
- rusty1s/pytorch_geometric
rusty1s/pytorch_geometric
23,848View on GitHubPyTorch Geometric is a library for building and training machine learning models on graph-structured data. It provides a framework for developing graph neural networks, including a specialized system for implementing node-to-node information exchange via customizable message passing, aggregation, and update functions. The library includes a sparse data processing toolkit that utilizes accelerated CPU and CUDA kernels to perform efficient reductions on large sparse datasets. It supports the creation of specialized architectures for structured data such as 3D meshes and point clouds. The proje
PyTorch Geometric is the flagship Python and PyTorch-based framework for building graph neural networks and generating node embeddings, perfectly matching the required support for scalability, inductive learning, and heterogeneous graphs.
PythonGraph Neural NetworksHeterogeneous Graph ModelingLarge-Scale Graph Training - williamleif/graphsage
williamleif/GraphSAGE
3,657View on GitHubGraphSAGE 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
GraphSAGE is a Python framework built for inductive representation learning and neighborhood aggregation on large-scale graphs, matching all the core requirements for generating neural node embeddings.
PythonInductive LearningLarge-Scale Graph TrainingGraph Neural Networks - dmlc/dgl
dmlc/dgl
14,283View on GitHubDGL 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 repository provides a comprehensive graph neural network framework implemented in Python, supporting large-scale graphs, heterogeneous structures, and node embedding generation as requested.
PythonHeterogeneous Graph ModelingHeterogeneous Graph ModelingLarge-Scale Graph Training - pyg-team/pytorch_geometric
pyg-team/pytorch_geometric
23,838View on GitHubThis project is a deep learning library designed for training neural networks on irregular data structures, including graphs, 3D meshes, and point clouds. It functions as an extension to the PyTorch framework, providing specialized layers and kernels that enable the processing of complex, non-Euclidean information. The library distinguishes itself through a geometric deep learning toolkit that manages the unique requirements of graph-based data. It utilizes sparse matrix-based message passing to aggregate information across nodes and employs dynamic computational graph construction to accommo
PyTorch Geometric is the leading graph neural network library built on PyTorch, offering extensive support for node embeddings, scalability, inductive learning, and heterogeneous graphs in Python.
PythonGraph Learning - tkipf/pygcn
tkipf/pygcn
5,404View on GitHubpygcn is a PyTorch library and framework for implementing graph convolutional networks. It provides tools for semi-supervised node classification and the generation of node embeddings from graph-structured data. The system converts graph nodes into low-dimensional vectors based on neighborhood patterns and local similarities. It enables the prediction of node labels by leveraging both a small set of labeled examples and the overall graph topology. The library covers relational data analysis and semi-supervised graph learning. It includes computational primitives for message passing, adjacenc
This repository provides a PyTorch-based framework for implementing graph convolutional networks and generating node embeddings, aligning with the core requirements despite its more specialized scope.
PythonGraph Neural NetworksGraph Neural Networks - stellargraph/stellargraph
stellargraph/stellargraph
3,061View on GitHubStellarGraph - Machine Learning on Graphs
StellarGraph is a Python library built on TensorFlow and Keras designed for machine learning on graphs, providing node embedding and graph neural network capabilities well-suited for representation learning.
PythonFrameworks and LibrariesGeneral Machine LearningGraph Machine Learning - google-deepmind/graph_nets
google-deepmind/graph_nets
5,402View on GitHubgraph_nets is a graph-structured deep learning framework and library for building message-passing neural networks. It provides tools for designing architectures that operate on nodes and edges to process and reason about data structured as graphs using TensorFlow. The framework implements a message-passing paradigm for iterative information exchange between nodes. This approach enables the development of models that can reason about complex graph-structured inputs for tasks such as path-finding and sorting, or serve as a predictor for the future states and trajectories of physical systems.
This repository provides a graph neural network framework for message-passing architectures and node representations, though it is built on TensorFlow rather than PyTorch and lacks some advanced scaling features.
PythonGraph Neural Networks - tkipf/gae
tkipf/gae
1,740View on GitHubImplementation of Graph Auto-Encoders in TensorFlow
This repository provides a TensorFlow implementation of graph auto-encoders for node embeddings, though it focuses on transductive learning and lacks the PyTorch integration and broader scalability features requested.
PythonGraph Neural Networks - phanein/deepwalk
phanein/deepwalk
2,757View on GitHubDeepWalk - Deep Learning for Graphs
DeepWalk is a graph machine learning library that implements unsupervised representation learning for nodes via random walks and Skip-gram, though it lacks modern inductive learning, heterogeneous graph support, and native PyTorch integration.
PythonGraph Neural Networks - snap-stanford/graphgym
snap-stanford/graphgym
1,893View on GitHubPlatform for designing and evaluating Graph Neural Networks (GNN)
GraphGym is a platform built for designing and evaluating graph neural networks that integrates with PyTorch, though it focuses more on experiment management and architecture search than being a general-purpose node embedding library.
PythonGraph Neural Networks - tkipf/gcn
tkipf/gcn
7,361View on GitHubThis 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
This is a pioneering graph neural network library for spectral convolutions and node embedding generation, though it lacks the advanced scalability, inductive learning, and heterogeneous graph support of modern multi-purpose frameworks.
PythonGraph Neural Networks - shenweichen/graphembedding
shenweichen/GraphEmbedding
3,844View on GitHubGraphEmbedding 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
GraphEmbedding is a Python-based node embedding framework that uses random walks and matrix factorization for graph representation learning, though it lacks modern graph neural network architectures and PyTorch integration.
PythonGraph Embedding GeneratorsDimensionality Reduction TechniquesGraph Neighborhood Sampling - seongjunyun/graph_transformer_networks
seongjunyun/Graph_Transformer_Networks
1,082View on GitHubGraphTransformerNetworks is a graph neural network framework implemented in PyTorch for learning structural representations and performing classification tasks on complex heterogeneous graphs and relational networks. The project provides automated preprocessing pipelines to transform raw graph datasets into standardized formats, alongside model training, forward passes, and gradient backpropagation executed through dynamic tensor operations. The architecture incorporates self-attention mechanisms applied directly to graph structures to learn contextual representations of nodes and edges ac
This repository provides a PyTorch implementation of Graph Transformer Networks, which serves as a specialized framework for graph machine learning and node representation, though it is scoped to a specific research paper rather than offering a general-purpose library.
Jupyter NotebookHeterogeneous Graph Modeling - alibaba/graph-learn
alibaba/graph-learn
1,341View on GitHubGraph-learn is a distributed graph processing engine and graph neural network framework designed for large-scale graph data. It provides specialized query interfaces to extract training subgraphs and node neighborhoods, enabling the construction and training of complex graph neural network models on massive datasets. The system integrates a real-time inference server to serve live predictions by sampling dynamic graphs with low latency while processing streaming graph updates. The project features a C++ core engine integration that executes graph sampling and tensor operations natively, coupl
Graph-Learn is an industrial graph neural network framework integrated with PyTorch and TensorFlow for large-scale graph learning, though it leans more toward distributed industrial execution than standard research-focused node embedding libraries.
C++Graph Neural Networks - dsgiitr/graph_nets
dsgiitr/graph_nets
1,237View on GitHubGraph 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
This repository provides educational PyTorch implementations of classical node embedding and graph neural network papers, fitting the category even though it is structured as a learning collection rather than a production-scale framework.
Jupyter NotebookInductive LearningGraph Neural Network Implementations - mdeff/cnn_graph
mdeff/cnn_graph
1,369View on GitHubCnn_graph is a graph convolutional network framework and graph signal processing library designed for machine learning research. It provides computational notebooks and code to process and classify graph-structured data by combining node features with an underlying adjacency matrix representation. The framework performs spectral graph convolutions through localized filters and accelerates filtering operations using truncated Chebyshev polynomials to avoid explicit graph Laplacian diagonalization. It includes a graph-structured data pipeline and sparse adjacency representations to handle irreg
This repository provides graph convolutional neural networks using spectral filtering, fitting the core category of graph machine learning frameworks even though it lacks the broader inductive and heterogeneous features of modern toolkits.
Jupyter NotebookGraph Neural Networks
