Improving the Efficiency of Human-in-the-Loop Systems: Adding Artificial to Human Experts
This addresses efficiency issues in human-in-the-loop systems for AI/ML applications, though it is incremental as it builds on existing HITL frameworks.
The study tackled the problem of high human effort in human-in-the-loop systems by proposing a hybrid system that uses artificial experts to classify unknown classes, reducing human effort and improving efficiency, with experiments showing it outperforms traditional systems on image classification benchmarks.
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.