Code for Self-Supervised Few-Shot Learning on Point Clouds paper at NeurIPS 2020
-
Updated
Oct 10, 2020 - Python
Code for Self-Supervised Few-Shot Learning on Point Clouds paper at NeurIPS 2020
Git repo for the paper "Physics-constrained predictive molecular latent space discovery with graph scattering variational autoencoder."
The GMols server providing functionalities to the GMols client.
Here there are some useful stuff I have written to work on topological data analysis. Some of the code was developed with specific datasets in mind, but most should generalize well.
Torch implementation of Marc Finzi's Equivariant MLP
Prediction of Absorption, Distribution, Metabolism and Excretion (ADME) properties of small molecules.
Backtracking algorithms solve problems by trying out solutions incrementally and undoing them if they lead to a dead end. It is a systematic method of trying out different solutions to a problem by incrementally building a solution and undoing it if it leads to an invalid state.
This repository is the implementation of the paper Semi-Supervised Classification With Graph Convolutional Networks (aka GCN) by Kipf et al., ICLR 2017.
Toolkit for omics network analysis and predictive modeling
StellarGraph - Machine Learning on Graphs
GDL-project
Graph Attention Networks (GATs)
High-Order Graph Convolutional Recurrent Neural Network
Experiments with custom conv layers that summarize, propagate, and leverage information about the spatial geometry of features.
Multi-label propagation on graphs with GraphSage
LCNN: End-to-End Wireframe Parsing
Website for Krama Lab @ IIT Hyderabad
Learning Representations via Spectral-Biased Random Walks on Graphs at ICJNN 2020
Add a description, image, and links to the geometric-deep-learning topic page so that developers can more easily learn about it.
To associate your repository with the geometric-deep-learning topic, visit your repo's landing page and select "manage topics."