# Graph Attention Auto-Encoders

arXiv: https://arxiv.org/abs/1905.10715 · HTML: https://mlsanity.com/paper/1905.10715/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2019.

## Built on by (most cited first, 30 of 41)

- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling](https://mlsanity.com/paper/2304.02806/) (2023)
- [SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training](https://mlsanity.com/paper/2307.08476/) (2023)
- [SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking](https://mlsanity.com/paper/2301.12458/) (2023)
- [GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space Reconstruction](https://mlsanity.com/paper/2308.09663/) (2023)
- [MAGIC: Detecting Advanced Persistent Threats via Masked Graph Representation Learning](https://mlsanity.com/paper/2310.09831/) (2023)
- [SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples](https://mlsanity.com/paper/2410.10365/) (2024)
- [Motif-aware Attribute Masking for Molecular Graph Pre-training](https://mlsanity.com/paper/2309.04589/) (2023)
- [Incomplete Contrastive Multi-View Clustering with High-Confidence Guiding](https://mlsanity.com/paper/2312.08697/) (2023)
- [Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning](https://mlsanity.com/paper/2206.12933/) (2022)
- [Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning](https://mlsanity.com/paper/2310.15523/) (2023)
- [Multilayer Graph Contrastive Clustering Network](https://mlsanity.com/paper/2112.14021/) (2021)
- [Mesh-based graph convolutional neural networks for modeling materials with microstructure](https://mlsanity.com/paper/2107.00090/) (2021)
- [NCAGC: A Neighborhood Contrast Framework for Attributed Graph Clustering](https://mlsanity.com/paper/2206.07897/) (2022)
- [A Comprehensive Survey on Graph Summarization with Graph Neural Networks](https://mlsanity.com/paper/2302.06114/) (2023)
- [Learning Persistent Community Structures in Dynamic Networks via Topological Data Analysis](https://mlsanity.com/paper/2401.03194/) (2024)
- [Graph Positional Autoencoders as Self-supervised Learners](https://mlsanity.com/paper/2505.23345/) (2025)
- [Graph Representation Learning with Massive Unlabeled Data for Rumor Detection](https://mlsanity.com/paper/2508.04252/) (2025)
- [LMAE4Eth: Generalizable and Robust Ethereum Fraud Detection by Exploring Transaction Semantics and Masked Graph Embedding](https://mlsanity.com/paper/2509.03939/) (2025)
- [Wasserstein Adversarially Regularized Graph Autoencoder](https://mlsanity.com/paper/2111.04981/) (2021)
- [Reconstructing Humpty Dumpty: Multi-feature Graph Autoencoder for Open Set Action Recognition](https://mlsanity.com/paper/2212.06023/) (2022)
- [UGMAE: A Unified Framework for Graph Masked Autoencoders](https://mlsanity.com/paper/2402.08023/) (2024)
- [HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning](https://mlsanity.com/paper/2410.10915/) (2024)
- [Seeing All From a Few: Nodes Selection Using Graph Pooling for Graph Clustering](https://mlsanity.com/paper/2105.05320/) (2021)
- [ReGAE: Graph autoencoder based on recursive neural networks](https://mlsanity.com/paper/2201.12165/) (2022)
- [Between-Sample Relationship in Learning Tabular Data Using Graph and Attention Networks](https://mlsanity.com/paper/2306.06772/) (2023)
- [Variational Graph Autoencoder for Heterogeneous Information Networks with Missing and Inaccurate Attributes](https://mlsanity.com/paper/2311.07929/) (2023)
- [Unsupervised Graph Attention Autoencoder for Attributed Networks using K-means Loss](https://mlsanity.com/paper/2311.12986/) (2023)
- [GraphPub: Generation of Differential Privacy Graph with High Availability](https://mlsanity.com/paper/2403.00030/) (2024)
- [Hybrid Ensemble Deep Graph Temporal Clustering for Spatiotemporal Data](https://mlsanity.com/paper/2409.12590/) (2024)

## Abstract (arXiv)

Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data, several graph auto-encoders have recently been proposed, but they neglect to reconstruct either the graph structure or node attributes. In this paper, we present the graph attention auto-encoder (GATE), a neural network architecture for unsupervised representation learning on graph-structured data. Our architecture is able to reconstruct graph-structured inputs, including both node attributes and the graph structure, through stacked encoder/decoder layers equipped with self-attention mechanisms. In the encoder, by considering node attributes as initial node representations, each layer generates new representations of nodes by attending over their neighbors' representations. In the decoder, we attempt to reverse the encoding process to reconstruct node attributes. Moreover, node representations are regularized to reconstruct the graph structure. Our proposed architecture does not need to know the graph structure upfront, and thus it can be applied to inductive learning. Our experiments demonstrate competitive performance on several node classification benchmark datasets for transductive and inductive tasks, even exceeding the performance of supervised learning baselines in most cases.