Search papers, labs, and topics across Lattice.
This paper introduces a non-parametric conditional anomaly detection method using soft harmonic functions to estimate label confidence and identify unusual data instances. The approach regularizes the harmonic function solution to prevent flagging isolated or boundary examples as anomalies. Experiments on synthetic, UCI ML, and real-world EHR datasets demonstrate the method's effectiveness in detecting unusual labels compared to baselines.
Spotting unusual labels in your data just got easier with a new method that avoids the pitfalls of flagging isolated or boundary cases as anomalies.
In this paper, we consider the problem of conditional anomaly detection that aims to identify data instances with an unusual response or a class label. We develop a new non-parametric approach for conditional anomaly detection based on the soft harmonic solution, with which we estimate the confidence of the label to detect anomalous mislabeling. We further regularize the solution to avoid the detection of isolated examples and examples on the boundary of the distribution support. We demonstrate the efficacy of the proposed method on several synthetic and UCI ML datasets in detecting unusual labels when compared to several baseline approaches. We also evaluate the performance of our method on a real-world electronic health record dataset where we seek to identify unusual patient-management decisions.
