Unsupervised anomaly detection of implausible electronic health records: a real-world evaluation in cancer registries

Review Computer Science, Theory & Methods

Deep Learning for Anomaly Detection: A Review

Guansong Pang et al.

Summary: Deep anomaly detection has emerged as a critical direction in the research field of anomaly detection, covering advancements in multiple categories of methods. Reviewing them can help us understand their advantages, disadvantages, and how they address challenges.

ACM COMPUTING SURVEYS (2021)

Add to Collection

Review Engineering, Electrical & Electronic

A Unifying Review of Deep and Shallow Anomaly Detection

Lukas Ruff et al.

Summary: Deep learning approaches have significantly enhanced anomaly detection performance on complex data sets, sparking a renewed interest in the field. Various new methods have been introduced, including those based on generative models, one-class classification, and reconstruction. It is crucial to bring these methods together and explore the underlying principles and connections between classic and novel approaches for future research and development in anomaly detection.

PROCEEDINGS OF THE IEEE (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

FAIROD: Fairness-aware Outlier Detection

Shubhranshu Shekhar et al.

Summary: Fairness and Outlier Detection (OD) are closely related, but the concept of fairness in OD has been overlooked in prior work. This study introduces FAIROD, a fairness-aware outlier detector that aims to achieve treatment parity, group fairness, and accurate high-risk sample detection within each group. Extensive experiments show that FAIROD produces fair outcomes with respect to protected variables while maintaining detection performance.

AIES '21: PROCEEDINGS OF THE 2021 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Toward Explainable Deep Anomaly Detection

Guansong Pang et al.

Summary: Deep learning for anomaly detection is a popular research area, but the lack of explainability has been a challenge. Various techniques have been introduced in recent years to improve the interpretability of anomaly detection results. This tutorial aims to promote the development of explainable deep anomaly detection algorithms.

KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING (2021)

Add to Collection

Review Computer Science, Theory & Methods