Apr 3, 2020 · We present a probabilistic framework for community discovery and link prediction for graph-structured data, based on a novel, gamma ladder variational ...
In this work, we develop a deep generative framework for graph-structured data that enjoys the natural advantages of stochastic blockmodels and graph neural ...
We present a probabilistic framework for community discov-ery and link prediction for graph-structured data, based on a novel, gamma ladder variational ...
May 15, 2024 · Bibliographic details on Graph Representation Learning via Ladder Gamma Variational Autoencoders.
Apr 3, 2020 · A probabilistic framework for community discovery and link prediction for graph-structured data, based on a novel, gamma ladder variational autoencoder (VAE) ...
Code for AAAI 2019 paper: Graph Representation Learning via Ladder Gamma Variational Autoencoders - Releases ...
Missing: via | Show results with:via
We have presented a novel, gamma ladder VAE model for graph-structured data, that enables us to infer multilayered embeddings (in form of multiple layers of ...
In addition to leveraging the representational power of multiple layers of stochastic variables via the ladder VAE architecture, our framework offers the ...
People also ask
What does a variational autoencoder do?
What is graph autoencoder?
What is one real world application of variational autoencoders (VAE) in anomaly detection?
When were variational autoencoders invented?
Mar 26, 2024 · In this paper, we propose the SLA-VGAE model for semi-supervised graph representation learning. Our model consists of a GCN encoder for node representation ...
Graph Representation Learning via Ladder Gamma Variational Autoencoders. A Sarkar, N Mehta, P Rai. Association for the Advancement of Artificial Intelligence ...