# OLGA: One-cLass Graph Autoencoder

arXiv: https://arxiv.org/abs/2406.09131 · HTML: https://mlsanity.com/paper/2406.09131/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 52 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [Graph Learning: A Survey](https://mlsanity.com/paper/2105.00696/) (2021)
- [One-Class Classification: Taxonomy of Study and Review of Techniques](https://mlsanity.com/paper/1312.0049/) (2013)
- [Faithful Multimodal Explanation for Visual Question Answering](https://mlsanity.com/paper/1809.02805/) (2018)
- [DAGAD: Data Augmentation for Graph Anomaly Detection](https://mlsanity.com/paper/2210.09766/) (2022)
- [Classifying Multilingual User Feedback using Traditional Machine Learning and Deep Learning](https://mlsanity.com/paper/1909.05504/) (2019)
- [Graph Representation Learning via Multi-task Knowledge Distillation](https://mlsanity.com/paper/1911.05700/) (2019)
- [Visualizing Graph Neural Networks with CorGIE: Corresponding a Graph to Its Embedding](https://mlsanity.com/paper/2106.12839/) (2021)
- [Self-supervised Representation Learning for Reliable Robotic Monitoring of Fruit Anomalies](https://mlsanity.com/paper/2109.10135/) (2021)

## Abstract (arXiv)

One-class learning (OCL) comprises a set of techniques applied when real-world problems have a single class of interest. The usual procedure for OCL is learning a hypersphere that comprises instances of this class and, ideally, repels unseen instances from any other classes. Besides, several OCL algorithms for graphs have been proposed since graph representation learning has succeeded in various fields. These methods may use a two-step strategy, initially representing the graph and, in a second step, classifying its nodes. On the other hand, end-to-end methods learn the node representations while classifying the nodes in one learning process. We highlight three main gaps in the literature on OCL for graphs: (i) non-customized representations for OCL; (ii) the lack of constraints on hypersphere parameters learning; and (iii) the methods' lack of interpretability and visualization. We propose One-cLass Graph Autoencoder (OLGA). OLGA is end-to-end and learns the representations for the graph nodes while encapsulating the interest instances by combining two loss functions. We propose a new hypersphere loss function to encapsulate the interest instances. OLGA combines this new hypersphere loss with the graph autoencoder reconstruction loss to improve model learning. OLGA achieved state-of-the-art results and outperformed six other methods with a statistically significant difference from five methods. Moreover, OLGA learns low-dimensional representations maintaining the classification performance with an interpretable model representation learning and results.