SHAP attribution profiles can identify complementary anomaly detectors whose divergence in explanations predicts non-overlapping detections, enabling stronger ensembles when high individual performance is maintained.
How to Evaluate the Quality of Unsupervised Anomaly Detection Algorithms?
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
When sufficient labeled data are available, classical criteria based on Receiver Operating Characteristic (ROC) or Precision-Recall (PR) curves can be used to compare the performance of un-supervised anomaly detection algorithms. However , in many situations, few or no data are labeled. This calls for alternative criteria one can compute on non-labeled data. In this paper, two criteria that do not require labels are empirically shown to discriminate accurately (w.r.t. ROC or PR based criteria) between algorithms. These criteria are based on existing Excess-Mass (EM) and Mass-Volume (MV) curves, which generally cannot be well estimated in large dimension. A methodology based on feature sub-sampling and aggregating is also described and tested, extending the use of these criteria to high-dimensional datasets and solving major drawbacks inherent to standard EM and MV curves.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
MetaEns trains on meta-datasets to predict marginal gains from adding models and uses a submodular-inspired objective with diversity discounting and risk regularization for greedy unsupervised ensemble selection, outperforming baselines on 39 datasets.
citing papers explorer
-
Analyzing Shapley Additive Explanations to Understand Anomaly Detection Algorithm Behaviors and Their Complementarity
SHAP attribution profiles can identify complementary anomaly detectors whose divergence in explanations predicts non-overlapping detections, enabling stronger ensembles when high individual performance is maintained.
-
Automatic Unsupervised Ensemble Outlier Model Selection--Extended Version
MetaEns trains on meta-datasets to predict marginal gains from adding models and uses a submodular-inspired objective with diversity discounting and risk regularization for greedy unsupervised ensemble selection, outperforming baselines on 39 datasets.