Semi-supervised vs unsupervised anomaly detection.
mediumAnswer
- Unsupervised: no labels; assumes normals dominate.
- Semi-supervised: only normal data labeled — train on clean normals, detect deviations (one-class SVM, deep SVDD, AE).
- Supervised: rare — a few labeled anomalies (PU learning, imbalanced classification).
- Rule: whenever you have even 20-50 confirmed anomaly examples, do semi-supervised evaluation or PU learning — it's a huge lift over pure unsupervised.
Check yourself — multiple choice
- Same thing
- Unsupervised (no labels, assume normals dominate) / semi-supervised (clean normal labeled) / supervised (rare, PU-learning); 20-50 anomaly labels are already a big lift
- Random
- Only supervised
AD label regimes: unsup / semi-sup (normal-only) / PU / supervised; leverage any labels.
#anomaly-detection
Practise Unsupervised Learning
214 interview questions in this topic.
Related questions
- What are the main approaches to anomaly detection?
- How do outliers affect k-means and how do you handle them?
- Isolation Forest — how does it detect anomalies?
- Local Outlier Factor (LOF) — how does it work?
- One-class SVM — mechanism and pitfalls.
- Elliptic envelope / robust Mahalanobis distance — when to use?