What is the name of the approach that learns from labeled and unlabeled data to generalize to unseen data?

Get ready for the GARP Risk and AI Exam with flashcards and multiple choice questions. Each question comes with hints and explanations. Prepare for success!

Semi-supervised learning uses both labeled and unlabeled data to improve learning. The distinction is whether the goal is to generalize to new, unseen data or just to label the specific unlabeled set you have. When the aim is to generalize to unseen instances, the approach is inductive semi-supervised learning. It trains a model on the combined data and then applies that learned function to new examples. Transductive semi-supervised learning, in contrast, focuses on labeling the given unlabeled data without necessarily producing a model that generalizes beyond that dataset. Unsupervised learning uses only unlabeled data with no labeled guidance. So the approach described—learning from labeled and unlabeled data to generalize to unseen data—is inductive semi-supervised learning.