# Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks

arXiv: https://arxiv.org/abs/1910.00942 · HTML: https://mlsanity.com/paper/1910.00942/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2019.

## Built on by (most cited first, 14 of 14)

- [Local Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2109.03856/) (2021)
- [Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Prediction](https://mlsanity.com/paper/2202.00961/) (2022)
- [SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2105.06228/) (2021)
- [Learning Graph Representations](https://mlsanity.com/paper/2102.02026/) (2021)
- [A Comprehensive Survey on Graph Summarization with Graph Neural Networks](https://mlsanity.com/paper/2302.06114/) (2023)
- [Sparsifying the Update Step in Graph Neural Networks](https://mlsanity.com/paper/2109.00909/) (2021)
- [Latent Conditional Diffusion-based Data Augmentation for Continuous-Time Dynamic Graph Model](https://mlsanity.com/paper/2407.08500/) (2024)
- [Graph Representation Learning for Energy Demand Data: Application to Joint Energy System Planning under Emissions Constraints](https://mlsanity.com/paper/2209.12035/) (2022)
- [Learning Spatio-Temporal Aggregations for Large-Scale Capacity Expansion Problems](https://mlsanity.com/paper/2303.08996/) (2023)
- [A Generative Framework for Predictive Modeling of Multiple Chronic Conditions Using Graph Variational Autoencoder and Bandit-Optimized Graph Neural Network](https://mlsanity.com/paper/2409.13671/) (2024)
- [Thematic recommendations on knowledge graphs using multilayer networks](https://mlsanity.com/paper/2105.05733/) (2021)
- [Are Graph Representation Learning Methods Robust to Graph Sparsity and Asymmetric Node Information?](https://mlsanity.com/paper/2205.09648/) (2022)
- [A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networks](https://mlsanity.com/paper/2410.21006/) (2024)
- [Aligning the Unseen in Attributed Graphs: Interplay between Graph Geometry and Node Attributes Manifold](https://mlsanity.com/paper/2601.22806/) (2026)

## Abstract (arXiv)

Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering. Graph AE, VAE and most of their extensions rely on graph convolutional networks (GCN) to learn vector space representations of nodes. In this paper, we propose to replace the GCN encoder by a simple linear model w.r.t. the adjacency matrix of the graph. For the two aforementioned tasks, we empirically show that this approach consistently reaches competitive performances w.r.t. GCN-based models for numerous real-world graphs, including the widely used Cora, Citeseer and Pubmed citation networks that became the de facto benchmark datasets for evaluating graph AE and VAE. This result questions the relevance of repeatedly using these three datasets to compare complex graph AE and VAE models. It also emphasizes the effectiveness of simple node encoding schemes for many real-world applications.