# To Share or Not to Share: Investigating Weight Sharing in Variational Graph Autoencoders

arXiv: https://arxiv.org/abs/2502.16724 · HTML: https://mlsanity.com/paper/2502.16724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 23 Feb 2025.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Community Detection and Stochastic Block Models](https://mlsanity.com/paper/1703.10146/) (2017)
- [Adversarially Regularized Graph Autoencoder for Graph Embedding](https://mlsanity.com/paper/1802.04407/) (2018)
- [Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap](https://mlsanity.com/paper/2008.01475/) (2020)
- [Dirichlet Graph Variational Autoencoder](https://mlsanity.com/paper/2010.04408/) (2020)
- [Gravity-Inspired Graph Autoencoders for Directed Link Prediction](https://mlsanity.com/paper/1905.09570/) (2019)
- [Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Prediction](https://mlsanity.com/paper/2202.00961/) (2022)
- [Simple and Effective Graph Autoencoders with One-Hop Linear Models](https://mlsanity.com/paper/2001.07614/) (2020)
- [Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders](https://mlsanity.com/paper/2108.01053/) (2021)
- [Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation](https://mlsanity.com/paper/2205.14651/) (2022)
- [New Frontiers in Graph Autoencoders: Joint Community Detection and Link Prediction](https://mlsanity.com/paper/2211.08972/) (2022)

## Abstract (arXiv)

This paper investigates the understudied practice of weight sharing (WS) in variational graph autoencoders (VGAE). WS presents both benefits and drawbacks for VGAE model design and node embedding learning, leaving its overall relevance unclear and the question of whether it should be adopted unresolved. We rigorously analyze its implications and, through extensive experiments on a wide range of graphs and VGAE variants, demonstrate that the benefits of WS consistently outweigh its drawbacks. Based on our findings, we recommend WS as an effective approach to optimize, regularize, and simplify VGAE models without significant performance loss.