PyTorch Geometric tutorial: Adversarial Regularizer (Variational) Graph Autoencoders

Показать описание

In this tutorial, we study how to improve GAE and VGAE by means of an adversarial regularizer.

Download the slides and the Jupyter-notebook from the official web site:

Antonio Longa

Рекомендации по теме

Комментарии

The audio is unfortunately not the easiest to follow. Would be great if we got corresponding English subtitles. I can only see Italian auto generated subtitles

debjyotighosh

I have another question. In DCGANs, which use conv2d to do convolution on Euclidean space，they used CONV2D-transform in the discriminator, why we don't need a similar method in ARGA but only use MLPs to construct the discriminator?

qiguosun

Thanks for your representation. I have a question, is there any method to decode the node features?

qiguosun

PyTorch Geometric tutorial: Adversarial Regularizer (Variational) Graph Autoencoders

PyTorch Geometric tutorial: Adversarial Regularizer (Variational) Graph Autoencoders

PyTorch Geometric tutorial: Graph Autoencoders & Variational Graph Autoencoders

Pytorch Geometric tutorial: Special Guest: Matthias Fey

Pytorch Geometric tutorial: DeepWalk and Node2Vec (Theory)

detach tensors from graph in PyTorch

Regularizing CNN Transfer Learning With Randomised Regression

Carola Schönlieb: Machine Learned Regularisation for Solving Inverse Problems

Distribution Augmentation for Generative Modeling

NTU ML2019SPRING - Pytorch Tutorial

RandAugment Paper Walkthrough

NeurIPS 2021 | ADGCL : Adversarial Graph Augmentation to Improve Graph Contrastive

Dynamical Variational Autoencoders (3/5)

Geometric Deep Learning on Graphs and Manifolds #NIPS2017

Tutorial on Deep Learning IV

GNN Project #4.1 - Graph Variational Autoencoders

Implementing Differentiable Optimal Transport: A Case Study

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation (ICCV 2021)

Light Field Spatial Super-Resolution via Deep Combinatorial Geometry Embedding and Structural...

Generative Adversarial Graph Convolutional Networks for Human Action Synthesis

Continuous Representation Of Molecules using Graph Variational Autoencoder by Mohammadamin Tavakoli

MLfAS - 08 Variational Autoencoder - 04 VAE Experiment 1: Variational Loss

DEEP LEARNING with PyTorch study group - 04/10/2021

Understanding geometric attributes with autoencoders. - Newson - Workshop 3 - CEB T1 2019

Tutorial on Generative adversarial networks - Connections between adversarial training and RL