# A Degeneracy Framework for Scalable Graph Autoencoders

arXiv: https://arxiv.org/abs/1902.08813 · HTML: https://mlsanity.com/paper/1902.08813/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Feb 2019.

## Built on by (most cited first, 12 of 12)

- [A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation](https://mlsanity.com/paper/2402.03358/) (2024)
- [MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2201.02534/) (2022)
- [Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Prediction](https://mlsanity.com/paper/2202.00961/) (2022)
- [A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps](https://mlsanity.com/paper/2106.03819/) (2021)
- [Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders](https://mlsanity.com/paper/2108.01053/) (2021)
- [Mask-GVAE: Blind Denoising Graphs via Partition](https://mlsanity.com/paper/2102.04228/) (2021)
- [Scaling R-GCN Training with Graph Summarization](https://mlsanity.com/paper/2203.02622/) (2022)
- [Subsampling Graphs with GNN Performance Guarantees](https://mlsanity.com/paper/2502.16703/) (2025)
- [Learning Graph Neural Networks using Exact Compression](https://mlsanity.com/paper/2304.14793/) (2023)
- [Normed Spaces for Graph Embedding](https://mlsanity.com/paper/2312.01502/) (2023)
- [New Frontiers in Graph Autoencoders: Joint Community Detection and Link Prediction](https://mlsanity.com/paper/2211.08972/) (2022)
- [Graph Sparsification for Enhanced Conformal Prediction in Graph Neural Networks](https://mlsanity.com/paper/2410.21618/) (2024)

## Abstract (arXiv)

In this paper, we present a general framework to scale graph autoencoders (AE) and graph variational autoencoders (VAE). This framework leverages graph degeneracy concepts to train models only from a dense subset of nodes instead of using the entire graph. Together with a simple yet effective propagation mechanism, our approach significantly improves scalability and training speed while preserving performance. We evaluate and discuss our method on several variants of existing graph AE and VAE, providing the first application of these models to large graphs with up to millions of nodes and edges. We achieve empirically competitive results w.r.t. several popular scalable node embedding methods, which emphasizes the relevance of pursuing further research towards more scalable graph AE and VAE.