# google-deepmind/graph_nets

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/google-deepmind-graph-nets).**

5,402 stars · 778 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/google-deepmind/graph_nets
- Homepage: https://arxiv.org/abs/1806.01261
- awesome-repositories: https://awesome-repositories.com/repository/google-deepmind-graph-nets.md

## Topics

`artificial-intelligence` `deep-learning` `graph-networks` `graphs` `neural-networks` `sonnet` `tensorflow`

## Description

graph_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.

## Tags

### Artificial Intelligence & ML

- [Graph Message Passing Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/graph-message-passing-frameworks.md) — Provides a framework for implementing message passing primitives to learn representations of nodes and edges in graphs.
- [Geometric Deep Learning Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/geometric-deep-learning-frameworks.md) — Provides a framework for applying deep learning to non-Euclidean data such as molecular graphs.
- [Graph Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/graph-neural-networks.md) — Provides a library for building neural network architectures designed to process data represented as graphs. ([source](https://cdn.jsdelivr.net/gh/google-deepmind/graph_nets@master/README.md))
- [Message Passing Primitives](https://awesome-repositories.com/f/artificial-intelligence-ml/message-passing-primitives.md) — Implements differentiable compute patterns for aggregating and updating features across graph topologies.
- [TensorFlow Graph Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/tensorflow-graph-execution.md) — Utilizes TensorFlow's computational graphs to execute mathematical operations on hardware accelerators.
- [Fixed-Point Convergence](https://awesome-repositories.com/f/artificial-intelligence-ml/fixed-point-convergence.md) — Processes graph information repeatedly until node and edge representations reach a stable state.
- [Graph Reasoning Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/graph-reasoning-systems.md) — Implements systems for reasoning over graph-structured data to perform tasks like path-finding and sorting. ([source](https://cdn.jsdelivr.net/gh/google-deepmind/graph_nets@master/README.md))
- [Iterative Prediction Refiners](https://awesome-repositories.com/f/artificial-intelligence-ml/model-predictions/prediction-engines/iterative-prediction-refiners.md) — Feeds model outputs back as inputs to iteratively refine predictions and simulate system evolution.

### Programming Languages & Runtimes

- [Graph Representations](https://awesome-repositories.com/f/programming-languages-runtimes/programming-utilities/data-structure-type-helpers/data-structures/dictionaries/graph-representations.md) — Provides data structures that store graph topology and edge attributes for neural network processing.

### Part of an Awesome List

- [Physical System Trajectories](https://awesome-repositories.com/f/awesome-lists/ai/trajectory-prediction/physical-system-trajectories.md) — Forecasts the future state of a physical system by iteratively feeding model predictions back as inputs. ([source](https://cdn.jsdelivr.net/gh/google-deepmind/graph_nets@master/README.md))

### Data & Databases

- [Graph Computation](https://awesome-repositories.com/f/data-databases/data-processing-pipelines/data-processing/distributed-processing-frameworks/distributed-computing/graph-computation.md) — Implements graph-based computation to perform complex tasks such as path-finding or sorting.

### Graphics & Multimedia

- [Physical System Trajectory Predictors](https://awesome-repositories.com/f/graphics-multimedia/physical-system-simulations/physical-system-trajectory-predictors.md) — Iteratively predicts the future state of physical systems by processing graph-based spatial data.