Graph Nets

graph_nets es un framework de aprendizaje profundo estructurado en grafos y una librería para construir redes neuronales de paso de mensajes. Proporciona herramientas para diseñar arquitecturas que operan sobre nodos y aristas para procesar y razonar sobre datos estructurados como grafos utilizando TensorFlow.

El framework implementa un paradigma de paso de mensajes para el intercambio iterativo de información entre nodos. Este enfoque permite el desarrollo de modelos que pueden razonar sobre entradas complejas estructuradas en grafos para tareas como la búsqueda de rutas y la clasificación, o servir como predictor para los estados futuros y trayectorias de sistemas físicos.

Features

Graph Message Passing Frameworks - Provides a framework for implementing message passing primitives to learn representations of nodes and edges in graphs.
Geometric Deep Learning Frameworks - Provides a framework for applying deep learning to non-Euclidean data such as molecular graphs.
Graph Neural Networks - Provides a library for building neural network architectures designed to process data represented as graphs.
Message Passing Primitives - Implements differentiable compute patterns for aggregating and updating features across graph topologies.
TensorFlow Graph Execution - Utilizes TensorFlow's computational graphs to execute mathematical operations on hardware accelerators.
Graph Representations - Provides data structures that store graph topology and edge attributes for neural network processing.
Fixed-Point Convergence - Processes graph information repeatedly until node and edge representations reach a stable state.
Graph Reasoning Systems - Implements systems for reasoning over graph-structured data to perform tasks like path-finding and sorting.
Iterative Prediction Refiners - Feeds model outputs back as inputs to iteratively refine predictions and simulate system evolution.
Physical System Trajectories - Forecasts the future state of a physical system by iteratively feeding model predictions back as inputs.
Graph Computation - Implements graph-based computation to perform complex tasks such as path-finding or sorting.
Physical System Trajectory Predictors - Iteratively predicts the future state of physical systems by processing graph-based spatial data.

Historial de estrellas

google-deepmindgraph_nets

Name: google-deepmind/graph_nets
Author: google-deepmind

View on GitHub

5,402 estrellas778 forksPythonApache-2.05 vistasarxiv.org/abs/1806.01261

Graph Nets

Features

Graph Message Passing Frameworks - Provides a framework for implementing message passing primitives to learn representations of nodes and edges in graphs.
Geometric Deep Learning Frameworks - Provides a framework for applying deep learning to non-Euclidean data such as molecular graphs.
Graph Neural Networks - Provides a library for building neural network architectures designed to process data represented as graphs.
Message Passing Primitives - Implements differentiable compute patterns for aggregating and updating features across graph topologies.
TensorFlow Graph Execution - Utilizes TensorFlow's computational graphs to execute mathematical operations on hardware accelerators.
Graph Representations - Provides data structures that store graph topology and edge attributes for neural network processing.
Fixed-Point Convergence - Processes graph information repeatedly until node and edge representations reach a stable state.
Graph Reasoning Systems - Implements systems for reasoning over graph-structured data to perform tasks like path-finding and sorting.
Iterative Prediction Refiners - Feeds model outputs back as inputs to iteratively refine predictions and simulate system evolution.
Physical System Trajectories - Forecasts the future state of a physical system by iteratively feeding model predictions back as inputs.
Graph Computation - Implements graph-based computation to perform complex tasks such as path-finding or sorting.
Physical System Trajectory Predictors - Iteratively predicts the future state of physical systems by processing graph-based spatial data.

Alternativas open-source a Graph Nets

Proyectos open-source similares, clasificados según cuántas características comparten con Graph Nets.

dmlc/dgl
dmlc/dgl
14,283Ver en GitHub
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
Pythondeep-learninggraph-neural-networks
Ver en GitHub14,283
rusty1s/pytorch_geometric
rusty1s/pytorch_geometric
23,848Ver en GitHub
PyTorch 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
Python
Ver en GitHub23,848
tkipf/pygcn
tkipf/pygcn
5,404Ver en GitHub
pygcn 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
Python
Ver en GitHub5,404

Preguntas frecuentes

¿Qué hace google-deepmind/graph_nets?

¿Cuáles son las características principales de google-deepmind/graph_nets?

Las características principales de google-deepmind/graph_nets son: Graph Message Passing Frameworks, Geometric Deep Learning Frameworks, Graph Neural Networks, Message Passing Primitives, TensorFlow Graph Execution, Graph Representations, Fixed-Point Convergence, Graph Reasoning Systems.

¿Qué alternativas de código abierto existen para google-deepmind/graph_nets?

Las alternativas de código abierto para google-deepmind/graph_nets incluyen: dmlc/dgl — DGL is a Python library for building and training graph neural networks. It functions as a graph message passing… rusty1s/pytorch_geometric — PyTorch Geometric is a library for building and training machine learning models on graph-structured data. It provides… tkipf/pygcn — pygcn is a PyTorch library and framework for implementing graph convolutional networks. It provides tools for… pageman/sutskever-30-implementations — This project is a collection of deep learning research implementations and a reproduction kit designed to translate… packtpublishing/hands-on-graph-neural-networks-using-python — This repository serves as an educational resource for implementing graph neural networks using Python. It provides a… charlesq34/pointnet2 — PointNet++ is a deep learning framework designed for processing and classifying 3D point cloud data. It utilizes a…