Learning to Complement Humans
This work addresses the challenge of enhancing collaborative efficiency in perceptual, diagnostic, and reasoning tasks for users in fields like science and medicine, representing a novel method rather than an incremental improvement.
The paper tackles the problem of optimizing human-machine team performance by training AI systems to focus on tasks difficult for humans while seeking human input for machine-difficult tasks, demonstrating in scientific discovery and medical diagnosis domains that these teams outperform individuals.
A rising vision for AI in the open world centers on the development of systems that can complement humans for perceptual, diagnostic, and reasoning tasks. To date, systems aimed at complementing the skills of people have employed models trained to be as accurate as possible in isolation. We demonstrate how an end-to-end learning strategy can be harnessed to optimize the combined performance of human-machine teams by considering the distinct abilities of people and machines. The goal is to focus machine learning on problem instances that are difficult for humans, while recognizing instances that are difficult for the machine and seeking human input on them. We demonstrate in two real-world domains (scientific discovery and medical diagnosis) that human-machine teams built via these methods outperform the individual performance of machines and people. We then analyze conditions under which this complementarity is strongest, and which training methods amplify it. Taken together, our work provides the first systematic investigation of how machine learning systems can be trained to complement human reasoning.