Improving the Efficiency of Human-in-the-Loop Systems: Adding Artificial to Human Experts

TL;DR

This paper introduces a hybrid AI-human system that creates artificial experts to reduce human effort in classifying difficult data, improving efficiency in human-in-the-loop systems.

Contribution

It proposes a novel hybrid system that learns from human-reviewed data to automatically classify unknown classes, reducing reliance on human experts.

Findings

Outperforms traditional HITL systems on image classification benchmarks

Reduces human effort over time in classifying difficult instances

Increases overall system efficiency and accuracy

Abstract

Information systems increasingly leverage artificial intelligence (AI) and machine learning (ML) to generate value from vast amounts of data. However, ML models are imperfect and can generate incorrect classifications. Hence, human-in-the-loop (HITL) extensions to ML models add a human review for instances that are difficult to classify. This study argues that continuously relying on human experts to handle difficult model classifications leads to a strong increase in human effort, which strains limited resources. To address this issue, we propose a hybrid system that creates artificial experts that learn to classify data instances from unknown classes previously reviewed by human experts. Our hybrid system assesses which artificial expert is suitable for classifying an instance from an unknown class and automatically assigns it. Over time, this reduces human effort and increases the efficiency of the system. Our experiments demonstrate that our approach outperforms traditional HITL systems for several benchmarks on image classification.