Relational Graph Neural Network Libraries
Frameworks and tools for implementing graph neural networks specifically designed to process complex relational data structures.
Relational Graph Neural Network Libraries
Find the best repos with AI.We'll search the best matching repositories with AI.
- 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 foundational framework for inductive graph representation learning that natively implements neighborhood aggregation and graph sampling, making it a direct fit for building graph neural networks on structured data.
PythonGraph Neighborhood SamplingNeighborhood AggregatorsNode Classification - 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
DGL is a comprehensive framework for graph neural networks that natively supports message passing, heterogeneous relational data, and large-scale graph sampling while integrating seamlessly with PyTorch and TensorFlow.
PythonGraph Neighborhood SamplingGraph Neighborhood SamplingHeterogeneous Graph Modeling - 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 library provides a specialized framework for spectral graph convolutions and node classification, serving as a foundational tool for graph-based deep learning despite its focus on spectral methods rather than general-purpose message passing.
PythonNode Classification - benedekrozemberczki/graphwaveletneuralnetwork
benedekrozemberczki/GraphWaveletNeuralNetwork
A PyTorch implementation of "Graph Wavelet Neural Network" (ICLR 2019)
This repository provides a PyTorch-based implementation of a specific graph neural network architecture, making it a suitable tool for performing deep learning on graph-structured data.
PythonGeometric Deep Learning: Graph & Irregular StructuresGraph Neural Networks - benedekrozemberczki/appnp
benedekrozemberczki/APPNP
A PyTorch implementation of "Predict then Propagate: Graph Neural Networks meet Personalized PageRank" (ICLR 2019).
This repository provides a PyTorch implementation of the APPNP architecture, which utilizes message passing to perform node classification on graph-structured data.
PythonGeometric Deep Learning: Graph & Irregular StructuresGraph Neural Networks - benedekrozemberczki/capsgnn
benedekrozemberczki/CapsGNN
1,278View on GitHubA PyTorch implementation of "Capsule Graph Neural Network" (ICLR 2019).
This repository provides a PyTorch-based implementation of a specific Capsule Graph Neural Network architecture, making it a functional tool for performing graph-based deep learning on structured data.
PythonGeometric Deep Learning: Graph & Irregular StructuresGraph Neural Networks
