Nov 21, 2016 · We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE). This model makes use of latent variables and is capable of learning interpretable latent representations for undirected graphs.

Sep 9, 2019 · Variational graph autoencoder (VGAE) applies the idea of VAE on graph-structured data, which significantly improves predictive performance on a number of citation network datasets such as Cora...

Graph Auto-Encoders (GAEs) are end-to-end trainable neural network models for unsupervised learning, clustering and link prediction on graphs. GAEs have successfully been used for: Matrix completion / recommendation with side information: R. Berg et al., Graph Convolutional Matrix Completion (2017).

We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE). This model makes use of latent variables and is capable of learning interpretable latent …

We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE) [2, 3]. This model makes use of latent variables and is ca-pable of learning interpretable latent representa-tions for undirected graphs (see Figure 1).

Apr 30, 2023 · In this paper, we propose a novel deep probabilistic model for graph analysis, termed Multi-head Variational Graph Autoencoder Constrained by Sum-product Networks (named SPN-MVGAE), which helps to relax the mean-field assumption and learns better latent representation with fault tolerance.

To mitigate such issues, we present three variants of graph variational autoencoder models for heterogeneous networks that avoid the computationally expensive sampling of meta-paths and maintain uncertainty estimates of node embeddings that help with better generalization.

Nov 14, 2023 · In this paper, we propose a generative self-supervised model GraMI to address these issues simultaneously. Specifically, GraMI first initializes all the nodes in the graph with a low-dimensional representation matrix.

Apr 30, 2025 · In this paper, we propose a novel recommendation framework named CVGAE (short for camouflaged variational graph autoencoder), which effectively models user behaviors and mitigates the risk of user attribute information leakage at the same time. Specifically, our CVGAE combines the strengths of VAEs in capturing latent features and variability ...

Oct 13, 2021 · This is how (and why) variational autoencoders work: they provide a better approximation to $\log p(x)$ by learning $q(z \mid x)$. We can think of $q(z \mid x)$ as a crutch for learning, since our end goal is still to optimize $\log p(x)$.