Gast ::
| Hauptseite > Workflowsammlungen > In Bearbeitung > DCFO: Density-Based Counterfactuals for Outliers |
| Hauptseite > Workflowsammlungen > In Bearbeitung > DCFO: Density-Based Counterfactuals for Outliers |
| Contribution to a conference proceedings/Contribution to a book | FZJ-2026-04957 |
; ; ; ;
2026
ACM New York, NY, USA
This record in other databases:
Please use a persistent id in citations: doi:10.1145/3770854.3780205
Abstract: Outlier detection identifies data points that significantly deviate from the majority of the data distribution. Explaining outliers is crucial for understanding the underlying factors that contribute to their detection, validating their significance, and identifying potential biases or errors. Effective explanations provide actionable insights, facilitating preventive measures to avoid similar outliers in the future. Counterfactual explanations clarify why specific data points are classified as outliers by identifying minimal changes required to alter their prediction. Although valuable, most existing counterfactual explanation methods overlook the unique challenges posed by outlier detection, and fail to target classical, widely adopted outlier detection algorithms. Local Outlier Factor (LOF) is one of the most popular unsupervised outlier detection methods, quantifying outlierness through relative local density. Despite LOF's widespread use across diverse applications, it lacks interpretability. To address this limitation, we introduce \emph{Density-based Counterfactuals for Outliers (DCFO)}, a novel method specifically designed to generate counterfactual explanations for LOF. DCFO partitions the data space into regions where LOF behaves smoothly, enabling efficient gradient-based optimisation. Extensive experimental validation on $50$ OpenML datasets demonstrates that DCFO consistently outperforms benchmarked competitors, offering superior proximity and validity of generated counterfactuals.
|
The record appears in these collections: |
PDF
Volltext