# Learning to Make Predictions on Graphs with Autoencoders

arXiv: https://arxiv.org/abs/1802.08352 · HTML: https://mlsanity.com/paper/1802.08352/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Feb 2018.

## Built on by (most cited first, 4 of 4)

- [Edge: Enriching Knowledge Graph Embeddings with External Text](https://mlsanity.com/paper/2104.04909/) (2021)
- [PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies](https://mlsanity.com/paper/2303.10704/) (2023)
- [Deep Learning in Single-Cell Analysis](https://mlsanity.com/paper/2210.12385/) (2022)
- [3D Neuron Morphology Analysis](https://mlsanity.com/paper/2212.07044/) (2022)

## Abstract (arXiv)

We examine two fundamental tasks associated with graph representation learning: link prediction and semi-supervised node classification. We present a novel autoencoder architecture capable of learning a joint representation of both local graph structure and available node features for the multi-task learning of link prediction and node classification. Our autoencoder architecture is efficiently trained end-to-end in a single learning stage to simultaneously perform link prediction and node classification, whereas previous related methods require multiple training steps that are difficult to optimize. We provide a comprehensive empirical evaluation of our models on nine benchmark graph-structured datasets and demonstrate significant improvement over related methods for graph representation learning. Reference code and data are available at https://github.com/vuptran/graph-representation-learning