Learning to Defer to a Population: A Meta-Learning Approach
This addresses the need for more flexible and robust autonomous systems in domains like healthcare and transportation by enabling adaptation to changing experts without retraining.
The paper tackles the problem of learning to defer (L2D) systems requiring re-training for new experts by developing a meta-learning approach that adapts to unseen experts at test-time using a small context set, achieving improved performance on benchmarks like image recognition and skin lesion diagnosis.
The learning to defer (L2D) framework allows autonomous systems to be safe and robust by allocating difficult decisions to a human expert. All existing work on L2D assumes that each expert is well-identified, and if any expert were to change, the system should be re-trained. In this work, we alleviate this constraint, formulating an L2D system that can cope with never-before-seen experts at test-time. We accomplish this by using meta-learning, considering both optimization- and model-based variants. Given a small context set to characterize the currently available expert, our framework can quickly adapt its deferral policy. For the model-based approach, we employ an attention mechanism that is able to look for points in the context set that are similar to a given test point, leading to an even more precise assessment of the expert's abilities. In the experiments, we validate our methods on image recognition, traffic sign detection, and skin lesion diagnosis benchmarks.