Pith. sign in

REVIEW 4 cited by

Unsupervised Representation Learning by Predicting Random Distances

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1912.12186 v2 pith:RQIV3BYT submitted 2019-12-22 cs.CV cs.LGstat.ML

Hu Wang , Guansong Pang , Chunhua Shen , Congbo Ma This is my paper
classification cs.CVcs.LGstat.ML
keywords datadistanceslearnlearningfeatureslabelledrandomtasks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. RGLD: Randomized Global-Local Density Estimation for Tabular Anomaly Detection

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    RGLD combines randomized global and local density estimation over feature-bagged views to achieve top AUROC wins and strong AUPRC on 47 tabular datasets while running 50-580x faster than deep detectors.

  2. Calibrating Tabular Anomaly Detection via Optimal Transport

    cs.LG 2026-02 conditional novelty 6.0 of 10

    CTAD calibrates anomaly scores via optimal transport distance on empirical and K-means structural distributions of normal data, yielding consistent gains across 34 tabular datasets and seven detector types.

  3. ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection

    cs.AI 2025-10 conditional novelty 6.0 of 10

    A new 20-dataset benchmark with textual metadata reports that zero-shot LLMs detect tabular anomalies better when given semantic context, but label descriptions embedded in the metadata may explain much of the gain.

  4. CITADEL: Continual Anomaly Detection for Enhanced Learning in IoT Intrusion Detection

    cs.CR 2025-08 reject novelty 4.0 of 10

    CITADEL combines self-supervised masked autoencoders with KL-divergence-based memory selection and a hierarchical buffer to detect IoT intrusions without attack labels while retaining old knowledge.

Pith tools