GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → tvayer → PSCN

tvayer / PSCN

Licence: other
A python implementation of Patchy-San Convolutional Network for Graph

Programming Languages

c
50402 projects - #5 most used programming language
Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Labels

graphscnnclassification

Projects that are alternatives of or similar to PSCN

ML4K-AI-Extension
Use machine learning in AppInventor, with easy training using text, images, or numbers through the Machine Learning for Kids website.
Stars: ✭ 18 (-53.85%)
Mutual labels:  classification
classification
Catalyst.Classification
Stars: ✭ 35 (-10.26%)
Mutual labels:  classification
10 days of deep learning
10 days 10 different practical applications of Deep Learning (primarily NLP) using Tensorflow and Keras
Stars: ✭ 28 (-28.21%)
Mutual labels:  classification
onelearn
Online machine learning methods
Stars: ✭ 14 (-64.1%)
Mutual labels:  classification
ml-workflow-automation
Python Machine Learning (ML) project that demonstrates the archetypal ML workflow within a Jupyter notebook, with automated model deployment as a RESTful service on Kubernetes.
Stars: ✭ 44 (+12.82%)
Mutual labels:  classification
YOLOv1 tensorflow
YOLOv1 tensorflow
Stars: ✭ 14 (-64.1%)
Mutual labels:  classification
auditor
Model verification, validation, and error analysis
Stars: ✭ 56 (+43.59%)
Mutual labels:  classification
egfr-att
Drug effect prediction using neural network
Stars: ✭ 17 (-56.41%)
Mutual labels:  classification
Point2Sequence
Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network
Stars: ✭ 34 (-12.82%)
Mutual labels:  classification
supervised-machine-learning
This repo contains regression and classification projects. Examples: development of predictive models for comments on social media websites; building classifiers to predict outcomes in sports competitions; churn analysis; prediction of clicks on online ads; analysis of the opioids crisis and an analysis of retail store expansion strategies using…
Stars: ✭ 34 (-12.82%)
Mutual labels:  classification
YetAnotherGraphPlugin
A simple plugin for creating graph-like assets for Unreal Engine 4
Stars: ✭ 30 (-23.08%)
Mutual labels:  graphs
simpleAICV-pytorch-ImageNet-COCO-training
SimpleAICV:pytorch training example on ImageNet(ILSVRC2012)/COCO2017/VOC2007+2012 datasets.Include ResNet/DarkNet/RetinaNet/FCOS/CenterNet/TTFNet/YOLOv3/YOLOv4/YOLOv5/YOLOX.
Stars: ✭ 276 (+607.69%)
Mutual labels:  classification
immuneML
immuneML is a platform for machine learning analysis of adaptive immune receptor repertoire data.
Stars: ✭ 41 (+5.13%)
Mutual labels:  classification
ros tensorflow
This repo introduces how to integrate Tensorflow framework into ROS with object detection API.
Stars: ✭ 39 (+0%)
Mutual labels:  classification
NIPS-Global-Paper-Implementation-Challenge
Selective Classification For Deep Neural Networks.
Stars: ✭ 11 (-71.79%)
Mutual labels:  classification
kaliningraph
🕸️ Graphs, finite fields and discrete dynamical systems in Kotlin
Stars: ✭ 62 (+58.97%)
Mutual labels:  graphs
Fraud-Detection-in-Online-Transactions
Detecting Frauds in Online Transactions using Anamoly Detection Techniques Such as Over Sampling and Under-Sampling as the ratio of Frauds is less than 0.00005 thus, simply applying Classification Algorithm may result in Overfitting
Stars: ✭ 41 (+5.13%)
Mutual labels:  classification
imgui
Dear ImGui Addons Branch = plain unmodified dear imgui plus some extra addon.
Stars: ✭ 348 (+792.31%)
Mutual labels:  graphs
ssj
Social Signal Processing for Android
Stars: ✭ 24 (-38.46%)
Mutual labels:  classification
mmrazor
OpenMMLab Model Compression Toolbox and Benchmark.
Stars: ✭ 644 (+1551.28%)
Mutual labels:  classification
View All Similar Projects ➔

PSCN is a python3 implementation of the paper "Learning Convolutional Neural Networks for Graphs" by Mathias Niepert, Mohamed Ahmed and Konstantin Kutzkov (https://arxiv.org/abs/1605.05273)

  • Requires : networkx >=2, keras, pynauty

  • To install pynauty :

    • Go to folder pynauty-0.6.0
    • Build pynauty : "make pynauty"
    • Set user : "make user-ins pynauty"
    • Install : "pip install ."

Questions about the paper :

  • There is no indication about the labeling procedure used for the classification : is it chosen among a bunch of procedures (which one ?) before the classification using Theorem 2, or is it fixed to one procedure (eigenvector centrality, degree, ...). In this implementation it is fixed to be the betweeness centrality.

  • The convolution seems to be made over the dicrete labels/attributes of the graph nodes in the classification (molecules represented by 0,1,2 etc for MUTAG, PTC..) : what is the sense of such a convolution ?

  • For "dummy nodes" (when the size of the receptive field is higher than the size of the graph) which node attribute should be used ??

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].