# Unsupervised Representation Learning by Predicting Random Distances

arXiv: https://arxiv.org/abs/1912.12186 · HTML: https://mlsanity.com/paper/1912.12186/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2019.

## Built on by (most cited first, 30 of 35)

- [Deep Isolation Forest for Anomaly Detection](https://mlsanity.com/paper/2206.06602/) (2022)
- [Explainable Deep Few-shot Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/2108.00462/) (2021)
- [Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation](https://mlsanity.com/paper/2112.10063/) (2021)
- [Deep Clustering based Fair Outlier Detection](https://mlsanity.com/paper/2106.05127/) (2021)
- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [Functional Anomaly Detection: a Benchmark Study](https://mlsanity.com/paper/2201.05115/) (2022)
- [Knowledge Graph Embedding: An Overview](https://mlsanity.com/paper/2309.12501/) (2023)
- [Generic Perceptual Loss for Modeling Structured Output Dependencies](https://mlsanity.com/paper/2103.10571/) (2021)
- [Applications of knowledge graphs for food science and industry](https://mlsanity.com/paper/2107.05869/) (2021)
- [Enhancing Unsupervised Anomaly Detection with Score-Guided Network](https://mlsanity.com/paper/2109.04684/) (2021)
- [UADB: Unsupervised Anomaly Detection Booster](https://mlsanity.com/paper/2306.01997/) (2023)
- [EntropyStop: Unsupervised Deep Outlier Detection with Loss Entropy](https://mlsanity.com/paper/2405.12502/) (2024)
- [OptIForest: Optimal Isolation Forest for Anomaly Detection](https://mlsanity.com/paper/2306.12703/) (2023)
- [Weakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR](https://mlsanity.com/paper/2408.03627/) (2024)
- [GradStop: Exploring Training Dynamics in Unsupervised Outlier Detection through Gradient](https://mlsanity.com/paper/2412.08501/) (2024)
- [Hypergraph-Guided Regex Filter Synthesis for Event-Based Anomaly Detection](https://mlsanity.com/paper/2509.06911/) (2025)
- [ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection](https://mlsanity.com/paper/2510.02060/) (2025)
- [Oriole: Thwarting Privacy against Trustworthy Deep Learning Models](https://mlsanity.com/paper/2102.11502/) (2021)
- [Outlier detection using flexible categorisation and interrogative agendas](https://mlsanity.com/paper/2312.12010/) (2023)
- [Self-Supervised Spatial-Temporal Normality Learning for Time Series Anomaly Detection](https://mlsanity.com/paper/2406.19770/) (2024)
- [Flexible categorization using formal concept analysis and Dempster-Shafer theory](https://mlsanity.com/paper/2408.15012/) (2024)
- [Contextual Learning for Anomaly Detection in Tabular Data](https://mlsanity.com/paper/2509.09030/) (2025)
- [EventADL: Open-Box Anomaly Detection and Localization Framework for Events in Cloud-Based Service Systems](https://mlsanity.com/paper/2605.00936/) (2026)
- [Clustered Hierarchical Anomaly and Outlier Detection Algorithms](https://mlsanity.com/paper/2103.11774/) (2021)
- [IPOF: An Extremely and Excitingly Simple Outlier Detection Booster via Infinite Propagation](https://mlsanity.com/paper/2108.00360/) (2021)
- [Semi-supervised Training for Knowledge Base Graph Self-attention Networks on Link Prediction](https://mlsanity.com/paper/2209.01350/) (2022)
- [A Latent Space Correlation-Aware Autoencoder for Anomaly Detection in Skewed Data](https://mlsanity.com/paper/2301.00462/) (2023)
- [Unleashing the Potential of Unsupervised Deep Outlier Detection through Automated Training Stopping](https://mlsanity.com/paper/2305.16777/) (2023)
- [Anomalous Change Point Detection Using Probabilistic Predictive Coding](https://mlsanity.com/paper/2405.15727/) (2024)
- [Local Pairwise Distance Matching for Backpropagation-Free Reinforcement Learning](https://mlsanity.com/paper/2507.11367/) (2025)

## Abstract (arXiv)

Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensional data. However, they often require large-scale labelled data to successfully learn such features, which significantly hinders their adaption into unsupervised learning tasks, such as anomaly detection and clustering, and limits their applications into critical domains where obtaining massive labelled data is prohibitively expensive. To enable unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected space. Random mapping is a theoretically proven approach to obtain approximately preserved distances. To well predict these random distances, the representation learner is optimised to learn genuine class structures that are implicitly embedded in the randomly projected space. Empirical results on 19 real-world datasets show that our learned representations substantially outperform a few state-of-the-art competing methods in both anomaly detection and clustering tasks. Code is available at https://git.io/RDP