Foundations
Semi-Supervised Learning
A training approach that mixes a small amount of labeled data with a large amount of unlabeled data to get the best of both.
Semi-supervised learning is a practical middle ground for when labeling is expensive but raw data is plentiful. The model learns from the few labeled examples you can afford and leans on the structure in the much larger unlabeled set to generalize better than labels alone would allow. It is common in domains like medical imaging where expert labels are scarce and costly.
Reference: Wikipedia: Semi-Supervised Learning
Related terms
Supervised Learning
Training a model on labeled examples, where each input comes paired with the correct answer.
Unsupervised Learning
Training a model on data with no labels, so it has to find structure and patterns on its own.
Self-Supervised Learning
A training approach where the data provides its own labels, like hiding part of an input and predicting it, which is how LLMs first learn language.
Training Data
The examples a model learns from, whose size, quality, and bias largely determine how the model turns out.