PetarV- / Dgi
Licence: mit
Deep Graph Infomax (https://arxiv.org/abs/1809.10341)
Stars: β 326
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Dgi
Minisom
π΄ MiniSom is a minimalistic implementation of the Self Organizing Maps
Stars: β 801 (+145.71%)
Mutual labels: neural-networks, unsupervised-learning
Paragraph Vectors
π A PyTorch implementation of Paragraph Vectors (doc2vec).
Stars: β 337 (+3.37%)
Mutual labels: neural-networks, unsupervised-learning
Gon
Gradient Origin Networks - a new type of generative model that is able to quickly learn a latent representation without an encoder
Stars: β 126 (-61.35%)
Mutual labels: neural-networks, unsupervised-learning
Pyod
A Python Toolbox for Scalable Outlier Detection (Anomaly Detection)
Stars: β 5,083 (+1459.2%)
Mutual labels: neural-networks, unsupervised-learning
Sealion
The first machine learning framework that encourages learning ML concepts instead of memorizing class functions.
Stars: β 278 (-14.72%)
Mutual labels: neural-networks, unsupervised-learning
Komputation
Komputation is a neural network framework for the Java Virtual Machine written in Kotlin and CUDA C.
Stars: β 295 (-9.51%)
Mutual labels: neural-networks
Simclr
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations by T. Chen et al.
Stars: β 293 (-10.12%)
Mutual labels: unsupervised-learning
100 Days Of Ml Code
100-Days-Of-ML-CodeδΈζη
Stars: β 16,797 (+5052.45%)
Mutual labels: unsupervised-learning
Lightnet
π Bringing pjreddie's DarkNet out of the shadows #yolo
Stars: β 322 (-1.23%)
Mutual labels: neural-networks
Cs231
Complete Assignments for CS231n: Convolutional Neural Networks for Visual Recognition
Stars: β 317 (-2.76%)
Mutual labels: neural-networks
Mlpractical
Machine Learning Practical course repository
Stars: β 295 (-9.51%)
Mutual labels: neural-networks
Pix2depth
DEPRECATED: Depth Map Estimation from Monocular Images
Stars: β 293 (-10.12%)
Mutual labels: neural-networks
Selflow
SelFlow: Self-Supervised Learning of Optical Flow
Stars: β 319 (-2.15%)
Mutual labels: unsupervised-learning
Deep Learning Papers
Papers about deep learning ordered by task, date. Current state-of-the-art papers are labelled.
Stars: β 3,054 (+836.81%)
Mutual labels: neural-networks
Neural Pipeline
Neural networks training pipeline based on PyTorch
Stars: β 315 (-3.37%)
Mutual labels: neural-networks
Segmentation models.pytorch
Segmentation models with pretrained backbones. PyTorch.
Stars: β 4,584 (+1306.13%)
Mutual labels: neural-networks
DGI
Deep Graph Infomax (VeliΔkoviΔ et al., ICLR 2019): https://arxiv.org/abs/1809.10341
Overview
Here we provide an implementation of Deep Graph Infomax (DGI) in PyTorch, along with a minimal execution example (on the Cora dataset). The repository is organised as follows:
-
data/
contains the necessary dataset files for Cora; -
models/
contains the implementation of the DGI pipeline (dgi.py
) and our logistic regressor (logreg.py
); -
layers/
contains the implementation of a GCN layer (gcn.py
), the averaging readout (readout.py
), and the bilinear discriminator (discriminator.py
); -
utils/
contains the necessary processing subroutines (process.py
).
Finally, execute.py
puts all of the above together and may be used to execute a full training run on Cora.
Reference
If you make advantage of DGI in your research, please cite the following in your manuscript:
@inproceedings{
velickovic2018deep,
title="{Deep Graph Infomax}",
author={Petar Veli{\v{c}}kovi{\'{c}} and William Fedus and William L. Hamilton and Pietro Li{\`{o}} and Yoshua Bengio and R Devon Hjelm},
booktitle={International Conference on Learning Representations},
year={2019},
url={https://openreview.net/forum?id=rklz9iAcKQ},
}
License
MIT
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].