Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Library to implement graph neural networks in PyTorch
| Date | Stars |
|---|---|
| 2026-07-31 | 274 |
| 2026-08-02 | 274 |
| 2026-08-03 | 274 |
| 2026-08-06 | 274 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Graph Neural Networks This is a PyTorch library to implement graph neural networks and graph recurrent neural networks. Any questions, comments or suggestions, please e-mail Fernando Gama at [email protected] and/or Luana Ruiz at [email protected]. An in-depth tutorial on a source localization example can be found [here](tutorial.ipynb). * [Introduction](#introduction) * [Code](#code) * [Dependencies](#dependencies) * [Datasets](#datasets) * [Libraries](#libraries) * [Architectures](#architectures) * [Examples](#examples) ([tutorial](tutorial.ipynb)) * [Version](#version) Whenever using any part of this code, please cite the following paper F. Gama, A. G. Marques, G. Leus, and A. Ribeiro, "[Convolutional Neural Network Architectures for Signals Supported on Graphs](http://ieeexplore.ieee.org/document/8579589)," _IEEE Trans. Signal Process._, vol. 67, no. 4, pp. 1034–1049, Feb. 2019. We note that some specific [architectures](#architectures) have specific paper citation to adequately acknowledge the respective contributors. Other papers on GNNs by the authors are E. Isufi, F. Gama, and A. Ribeiro, "[EdgeNets: Edge Varying Graph Neural Networks](http://arxiv.org/abs/2001.07620)," submitted to _IEEE Trans. Pattern Analysis and Mach. Intell._ F. Gama, E. Isufi, G. Leus, and A. Ribeiro, "[Graphs, Convolutions, and Neural Networks](http://arxiv.org/abs/2003.03777)," submitted to _IEEE Signal Process. Mag._ L. Ruiz, F. Gama, and A. Ribeiro, "[Gated Graph Recurrent Neural Networks](http://arxiv.org/abs/2002.01038)," submitted to _IEEE Trans. Signal Process._ F. Gama, J. Bruna, and A. Ribeiro, "[Stability Properties of Graph Neural Networks](http://arxiv.org/abs/1905.04497)," submitted to _IEEE Trans. Signal Process._ F. Gama, E. Tolstaya, and A. Ribeiro, "[Graph Neural Networks for Decentralized Controllers](http://arxiv.org/abs/2003.10280)," _arXiv:2003.10280v1 [cs.LG],_ 23 March 2020. L. Ruiz, F. Gama, A. G. Marques, and A. Ribeiro, "[Invariance-Preserving Localized Activation Functions for Graph Neural Networks](https://ieeexplore.ieee.org/document/8911416)," _IEEE Trans. Signal Process._, vol. 68, no. 1, pp. 127-141, Jan. 2020. F. Gama, J. Bruna, and A. Ribeiro, "[Stability of Graph Scattering Transforms](http://arxiv.org/abs/1906.04784)," in _33rd Conf. Neural Inform. Process. Syst._ Vancouver, BC: Neural Inform. Process. Syst. Foundation, 8-14 Dec. 2019. F. Gama, A. G. Marques, A. Ribeiro, and G. Leus, "[MIMO Graph Filters for Convolutional Networks](http://ieeexplore.ieee.org/document/8445934)," in _19th IEEE Int. Workshop Signal Process. Advances in Wireless Commun._ Kalamata, Greece: IEEE, 25-28 June 2018, pp. 1–5. F. Gama, G. Leus, A. G. Marques, and A. Ribeiro, "[Convolutional Neural Networks via Node-Varying Graph Filters](https://ieeexplore.ieee.org/document/8439899)," in _2018 IEEE Data Sci. Workshop._ Lausanne, Switzerland: IEEE, 4-6 June 2018, pp. 220–224. ## Introduction <a class="anchor" id="introduction"></a> We consider data supported by an underlying graph with _N_ nodes. We describe the graph in terms of an _N x N_ matrix _S_ that respects the sparsity of the graph. That is, the element _(i,j)_ of matrix _S_ can be nonzero, if and only if, _i=j_ or _(j,i)_ is an edge of the graph. Examples of such matrices are the adjacency matrix, the graph Laplacian, the Markov matrix, and many normalized counterparts. In general, we refer to this matrix _S_ as the __graph shift operator__ (GSO). This code supports extension to a tensor GSO whenever we want to assign a vector weight to each edge, instead of a scalar weight. To describe the _N_-dimensional data _x_ as supported by the graph, we assume that each element of _x_ represents the data value at each node, i.e. the _i_-th element _[x]<sub>i</sub> = x<sub>i</sub>_ represents the data value at node _i_. We thus refer to _x_ as a __graph signal__. To effectively relate the graph signal _x_ (which is an _N_-dimensional vector) to the un
Excerpt of 34,401 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:661f4c851a85fbea, llm:description: 'Library to implement graph neural networks in PyTorch'
matched fp:661f4c851a85fbea, llm:description: 'Library to implement graph neural networks in PyTorch'
matched fp:661f4c851a85fbea, llm:description: 'Library to implement graph neural networks in PyTorch'