# Graph Autoencoders with Deconvolutional Networks

arXiv: https://arxiv.org/abs/2012.11898 · HTML: https://mlsanity.com/paper/2012.11898/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Prediction](https://mlsanity.com/paper/2202.00961/) (2022)
- [Semi-Supervised Hierarchical Graph Classification](https://mlsanity.com/paper/2206.05416/) (2022)
- [Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning](https://mlsanity.com/paper/2206.12933/) (2022)
- [Handling Missing Data via Max-Entropy Regularized Graph Autoencoder](https://mlsanity.com/paper/2211.16771/) (2022)
- [The quest for the GRAph Level autoEncoder (GRALE)](https://mlsanity.com/paper/2505.22109/) (2025)
- [Large-Scale Auto-Regressive Modeling Of Street Networks](https://mlsanity.com/paper/2209.00281/) (2022)
- [New Frontiers in Graph Autoencoders: Joint Community Detection and Link Prediction](https://mlsanity.com/paper/2211.08972/) (2022)
- [GRASPED: Graph Anomaly Detection using Autoencoder with Spectral Encoder and Decoder (Full Version)](https://mlsanity.com/paper/2508.15633/) (2025)
- [Decision Support System for Chronic Diseases Based on Drug-Drug Interactions](https://mlsanity.com/paper/2303.02405/) (2023)

## Abstract (arXiv)

Recent studies have indicated that Graph Convolutional Networks (GCNs) act as a low pass filter in spectral domain and encode smoothed node representations. In this paper, we consider their opposite, namely Graph Deconvolutional Networks (GDNs) that reconstruct graph signals from smoothed node representations. We motivate the design of Graph Deconvolutional Networks via a combination of inverse filters in spectral domain and de-noising layers in wavelet domain, as the inverse operation results in a high pass filter and may amplify the noise. Based on the proposed GDN, we further propose a graph autoencoder framework that first encodes smoothed graph representations with GCN and then decodes accurate graph signals with GDN. We demonstrate the effectiveness of the proposed method on several tasks including unsupervised graph-level representation , social recommendation and graph generation