A Reliable Framework for Human-in-the-Loop Anomaly Detection in Time Series

TL;DR

HILAD is a new human-in-the-loop framework that improves time series anomaly detection by enabling experts to interpret, detect issues, and correct model biases through an interactive visual interface, enhancing model reliability.

Contribution

The paper introduces HILAD, a novel bidirectional framework that integrates human expertise into anomaly detection models via visualization, addressing limitations of existing explanation methods.

Findings

HILAD improves model understanding and trust among users.

Users can effectively identify and correct model biases.

The framework enhances anomaly detection accuracy across datasets.

Abstract

Time series anomaly detection is a critical machine learning task for numerous applications, such as finance, healthcare, and industrial systems. However, even high-performing models may exhibit potential issues such as biases, leading to unreliable outcomes and misplaced confidence. While model explanation techniques, particularly visual explanations, offer valuable insights by elucidating model attributions of their decision, many limitations still exist -- They are primarily instance-based and not scalable across the dataset, and they provide one-directional information from the model to the human side, lacking a mechanism for users to address detected issues. To fulfill these gaps, we introduce HILAD, a novel framework designed to foster a dynamic and bidirectional collaboration between humans and AI for enhancing anomaly detection models in time series. Through our visual interface, HILAD empowers domain experts to detect, interpret, and correct unexpected model behaviors at scale. Our evaluation through user studies with two models and three time series datasets demonstrates the effectiveness of HILAD, which fosters a deeper model understanding, immediate corrective actions, and model reliability enhancement.