diff --git a/GNNGraphs/README.md b/GNNGraphs/README.md
index aadfe7936..c54c5614b 100644
--- a/GNNGraphs/README.md
+++ b/GNNGraphs/README.md
@@ -1,7 +1,36 @@
# GNNGraphs.jl
+[](https://juliagraphs.org/GraphNeuralNetworks.jl/docs/GraphNeuralNetworks.jl/)
+
A package implementing graph types for graph deep learning.
-This package is currently under development and may break frequentely.
-It is not meant for final users but for GNN libraries developers.
-Final user should use GraphNeuralNetworks.jl instead.
+The package is part of the [GraphNeuralNetworks.jl ecosystem](https://github.com/JuliaGraphs/GraphNeuralNetworks.jl) and is re-exported by the frontend packages [GraphNeuralNetworks.jl](https://juliagraphs.org/GraphNeuralNetworks.jl/docs/GraphNeuralNetworks.jl/) and [GNNLux.jl](https://juliagraphs.org/GraphNeuralNetworks.jl/docs/GNNLux.jl/).
+
+## Installation
+
+Install through the Julia package manager.
+
+```julia
+pkg> add GNNGraphs
+```
+
+## Usage
+
+For a comprehensive introduction to the library, refer to the [Documentation](https://juliagraphs.org/GraphNeuralNetworks.jl/docs/GNNGraphs.jl/).
+
+
+## Citing
+
+If you use GraphNeuralNetworks.jl in a scientific publication, we would appreciate a reference
+to [our paper](https://arxiv.org/abs/2412.06354):
+
+```
+@article{lucibello2024graphneuralnetworks,
+ title={GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia},
+ author={Lucibello, Carlo and Rossi, Aurora},
+ journal={arXiv preprint arXiv:2412.06354},
+ url={https://arxiv.org/abs/2412.06354},
+ year={2024}
+}
+```
+
diff --git a/GNNLux/README.md b/GNNLux/README.md
index 9970a88a8..5a77316b0 100644
--- a/GNNLux/README.md
+++ b/GNNLux/README.md
@@ -1,2 +1,48 @@
+
+
# GNNLux.jl
+[](https://juliagraphs.org/GraphNeuralNetworks.jl/docs/GNNLux.jl/)
+
+Graph convolutional layers based on the deep learning framework [Lux.jl](https://lux.csail.mit.edu/stable/).
+This is the frontend package for Lux users of the [GraphNeuralNetworks.jl ecosystem](https://github.com/JuliaGraphs/GraphNeuralNetworks.jl).
+
+
+### Features
+
+**GNNLux.jl** supports the following features:
+
+- Implementation of common graph convolutional layers.
+- Computation on batched graphs.
+- Custom layer definitions.
+- Support for CUDA and AMDGPU.
+- Integration with [Graphs.jl](https://github.com/JuliaGraphs/Graphs.jl).
+- [Examples](https://github.com/JuliaGraphs/GraphNeuralNetworks.jl/tree/master/GraphNeuralNetworks/examples) of node, edge, and graph-level machine learning tasks.
+- Heterogeneous and dynamical graphs and convolutions.
+
+## Installation
+
+Install through the Julia package manager.
+
+```julia
+pkg> add GNNLux
+```
+
+## Usage
+
+For a comprehensive introduction to the library, refer to the [Documentation](https://juliagraphs.org/GraphNeuralNetworks.jl/docs/GNNLux.jl/).
+
+## Citing
+
+If you use GraphNeuralNetworks.jl in a scientific publication, we would appreciate a reference
+to [our paper](https://arxiv.org/abs/2412.06354):
+
+```
+@article{lucibello2024graphneuralnetworks,
+ title={GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia},
+ author={Lucibello, Carlo and Rossi, Aurora},
+ journal={arXiv preprint arXiv:2412.06354},
+ url={https://arxiv.org/abs/2412.06354},
+ year={2024}
+}
+```
\ No newline at end of file
diff --git a/GNNlib/README.md b/GNNlib/README.md
index adc9991ab..22f75f8b4 100644
--- a/GNNlib/README.md
+++ b/GNNlib/README.md
@@ -1,13 +1,8 @@
# GNNlib.jl
-This package contains a collection deep-learning framework agnostic
-building blocks for graph neural networks such as message passing operators and implementations of graph convolutional layers.
+This package contains a collection framework-agnostic
+building blocks for deep learning on graphs such as message passing operators and implementations of graph convolutional layers.
-In the future it will serve as the foundation of GraphNeuralNetworks.jl (based on Flux,jl).
-GNNlib.jl will be to GraphNeuralNetworks.jl what NNlib.jl is to Flux.jl and Lux.jl.
-
-This package is currently under development and may break frequentely.
-It is not meant for final users but for GNN libraries developers.
-Final user should use GraphNeuralNetworks.jl instead.
+See [GraphNeuralNetworks.jl](https://juliagraphs.org/GraphNeuralNetworks.jl/docs/GraphNeuralNetworks.jl/) for a Flux-based frontend package that uses this library and [GNNLux.jl](https://juliagraphs.org/GraphNeuralNetworks.jl/docs/GNNLux.jl/) for a Lux-based one.
diff --git a/GraphNeuralNetworks/README.md b/GraphNeuralNetworks/README.md
index 565ee8f42..a57e542b9 100644
--- a/GraphNeuralNetworks/README.md
+++ b/GraphNeuralNetworks/README.md
@@ -1,29 +1,28 @@
-
-
+
# GraphNeuralNetworks.jl
-[](https://JuliaGraphs.github.io/GraphNeuralNetworks.jl/stable)
-[](https://JuliaGraphs.github.io/GraphNeuralNetworks.jl/dev)
-
-[](https://codecov.io/gh/JuliaGraphs/GraphNeuralNetworks.jl)
+[](https://juliagraphs.org/GraphNeuralNetworks.jl/docs/GraphNeuralNetworks.jl/)
+
+Graph convolutional layers based on the deep learning framework [Flux.jl](https://fluxml.ai/).
+This is the frontend package for Flux users of the [GraphNeuralNetworks.jl ecosystem](https://github.com/JuliaGraphs/GraphNeuralNetworks.jl).
-GraphNeuralNetworks.jl is a graph neural network library written in Julia and based on the deep learning framework [Flux.jl](https://github.com/FluxML/Flux.jl).
+### Features
-Among its features:
+**GraphNeuralNetworks.jl** supports the following features:
-* Implements common graph convolutional layers.
-* Supports computations on batched graphs.
-* Easy to define custom layers.
-* CUDA support.
-* Integration with [Graphs.jl](https://github.com/JuliaGraphs/Graphs.jl).
-* [Examples](https://github.com/JuliaGraphs/GraphNeuralNetworks.jl/tree/master/examples) of node, edge, and graph level machine learning tasks.
-* Heterogeneous and temporal graphs.
+- Implementation of common graph convolutional layers.
+- Computation on batched graphs.
+- Custom layer definitions.
+- Support for CUDA and AMDGPU.
+- Integration with [Graphs.jl](https://github.com/JuliaGraphs/Graphs.jl).
+- [Examples](https://github.com/JuliaGraphs/GraphNeuralNetworks.jl/tree/master/GraphNeuralNetworks/examples) of node, edge, and graph-level machine learning tasks.
+- Heterogeneous and dynamical graphs and convolutions.
-## Installation
+## Installation
-GraphNeuralNetworks.jl is a registered Julia package. You can easily install it through the package manager:
+Install the package through the Julia package manager.
```julia
pkg> add GraphNeuralNetworks
@@ -31,25 +30,19 @@ pkg> add GraphNeuralNetworks
## Usage
-Usage examples can be found in the [examples](https://github.com/JuliaGraphs/GraphNeuralNetworks.jl/tree/master/examples) and in the [notebooks](https://github.com/JuliaGraphs/GraphNeuralNetworks.jl/tree/master/notebooks) folder. Also, make sure to read the [documentation](https://JuliaGraphs.github.io/GraphNeuralNetworks.jl/dev) for a comprehensive introduction to the library.
-
+For a comprehensive introduction to the library, refer to the [Documentation](https://juliagraphs.org/GraphNeuralNetworks.jl/docs/GraphNeuralNetworks.jl/).
## Citing
-If you use GraphNeuralNetworks.jl in a scientific publication, we would appreciate the following reference:
+If you use GraphNeuralNetworks.jl in a scientific publication, we would appreciate a reference
+to [our paper](https://arxiv.org/abs/2412.06354):
```
-@misc{Lucibello2021GNN,
- author = {Carlo Lucibello and other contributors},
- title = {GraphNeuralNetworks.jl: a geometric deep learning library for the Julia programming language},
- year = 2021,
- url = {https://github.com/JuliaGraphs/GraphNeuralNetworks.jl}
+@article{lucibello2024graphneuralnetworks,
+ title={GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia},
+ author={Lucibello, Carlo and Rossi, Aurora},
+ journal={arXiv preprint arXiv:2412.06354},
+ url={https://arxiv.org/abs/2412.06354},
+ year={2024}
}
-```
-
-## Acknowledgments
-
-GraphNeuralNetworks.jl is largely inspired by [PyTorch Geometric](https://pytorch-geometric.readthedocs.io/en/latest/), [Deep Graph Library](https://docs.dgl.ai/),
-and [GeometricFlux.jl](https://fluxml.ai/GeometricFlux.jl/stable/).
-
-
+```
\ No newline at end of file
diff --git a/README.md b/README.md
index 6ab514c8a..b8f39cfa1 100644
--- a/README.md
+++ b/README.md
@@ -9,13 +9,13 @@
[](https://codecov.io/gh/JuliaGraphs/GraphNeuralNetworks.jl)
-**Libraries for deep learning on graphs in Julia**, using either [Flux.jl](https://fluxml.ai/Flux.jl/stable/) or [Lux.jl](https://lux.csail.mit.edu/stable/) as backend frameworks.
+**Libraries for deep learning on graphs in Julia**, using either [Flux.jl](https://fluxml.ai/) or [Lux.jl](https://lux.csail.mit.edu/stable/) as backend frameworks.
This repository contains the following packages:
-- **GraphNeuralNetworks.jl**: Provides graph convolutional layers based on the deep learning framework [Flux.jl](https://fluxml.ai/Flux.jl/stable/). This is the frontend package for Flux users.
+- **GraphNeuralNetworks.jl**: Provides graph convolutional layers based on the deep learning framework [Flux.jl](https://fluxml.ai/). This is the frontend package for Flux users.
-- **GNNLux.jl**: Offers graph convolutional layers based on the deep learning framework [Lux.jl](https://lux.csail.mit.edu/stable/). This is the frontend package for Lux users.
+- **GNNLux.jl**: Offers graph convolutional layers based on the deep learning framework [Lux.jl](https://lux.csail.mit.edu/). This is the frontend package for Lux users.
- **GNNGraphs.jl**: Provides graph data structures and helper functions for working with graph data. This package is re-exported by the frontend packages.
@@ -31,7 +31,7 @@ Both **GraphNeuralNetworks.jl** and **GNNLux.jl** support the following features
- Support for CUDA and AMDGPU.
- Integration with [Graphs.jl](https://github.com/JuliaGraphs/Graphs.jl).
- [Examples](https://github.com/JuliaGraphs/GraphNeuralNetworks.jl/tree/master/GraphNeuralNetworks/examples) of node, edge, and graph-level machine learning tasks.
-- Support for heterogeneous and temporal graphs.
+- Heterogeneous and dynamical graphs and convolutions.
## Installation
@@ -57,14 +57,16 @@ For a comprehensive introduction to the library, refer to the [Documentation](ht
## Citing
-If you use GraphNeuralNetworks.jl in a scientific publication, we would appreciate the following reference:
+If you use GraphNeuralNetworks.jl in a scientific publication, we would appreciate a reference
+to [our paper](https://arxiv.org/abs/2412.06354):
```
-@misc{Lucibello2021GNN,
- author = {Carlo Lucibello and other contributors},
- title = {GraphNeuralNetworks.jl: a geometric deep learning library for the Julia programming language},
- year = 2021,
- url = {https://github.com/JuliaGraphs/GraphNeuralNetworks.jl}
+@article{lucibello2024graphneuralnetworks,
+ title={GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia},
+ author={Lucibello, Carlo and Rossi, Aurora},
+ journal={arXiv preprint arXiv:2412.06354},
+ url={https://arxiv.org/abs/2412.06354},
+ year={2024}
}
```