# Epitomic Variational Graph Autoencoder

arXiv: https://arxiv.org/abs/2004.01468 · HTML: https://mlsanity.com/paper/2004.01468/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [Local Disentanglement in Variational Auto-Encoders Using Jacobian L1 Regularization](https://mlsanity.com/paper/2106.02923/) (2021)
- [A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks](https://mlsanity.com/paper/2108.03953/) (2021)
- [Barlow Graph Auto-Encoder for Unsupervised Network Embedding](https://mlsanity.com/paper/2110.15742/) (2021)
- [Learning Network Representations with Disentangled Graph Auto-Encoder](https://mlsanity.com/paper/2402.01143/) (2024)
- [Variational Embeddings for Community Detection and Node Representation](https://mlsanity.com/paper/2101.03885/) (2021)
- [Soft-Constrained Optimization of Latent Space in Variational Autoencoders](https://mlsanity.com/paper/2607.23751/) (2026)
- [Generalized Graph Variational Autoencoders: Bounded Divergences Control Posterior Collapse](https://mlsanity.com/paper/2609.29546/) (2026)

## Abstract (arXiv)

Variational autoencoder (VAE) is a widely used generative model for learning latent representations. Burda et al. in their seminal paper showed that learning capacity of VAE is limited by over-pruning. It is a phenomenon where a significant number of latent variables fail to capture any information about the input data and the corresponding hidden units become inactive. This adversely affects learning diverse and interpretable latent representations. As variational graph autoencoder (VGAE) extends VAE for graph-structured data, it inherits the over-pruning problem. In this paper, we adopt a model based approach and propose epitomic VGAE (EVGAE),a generative variational framework for graph datasets which successfully mitigates the over-pruning problem and also boosts the generative ability of VGAE. We consider EVGAE to consist of multiple sparse VGAE models, called epitomes, that are groups of latent variables sharing the latent space. This approach aids in increasing active units as epitomes compete to learn better representation of the graph data. We verify our claims via experiments on three benchmark datasets. Our experiments show that EVGAE has a better generative ability than VGAE. Moreover, EVGAE outperforms VGAE on link prediction task in citation networks.