Concept dictionary
Self-Supervised Learning
Self-supervised training is a method where the training signal is derived from the data itself, rather than from human-provided labels.
- Review state
- Reviewed in POC
- Freshness
- Current
- Version
- 2
Also called
- Self-Supervised Learning
- Self-Supervised Training
Remember it this wayThe data supplies the training signal.
In plain language
Self-supervised learning creates a training signal from the structure of the data itself. The system may hide, transform, or relate parts of an example and learn by predicting the missing or connected information.
Why it matters
It can use large amounts of unlabeled data, reducing the need for manual annotation. The task design still determines what patterns the model is encouraged to learn.
Example
A language model learns by predicting masked or next tokens drawn from the surrounding text rather than from labels written by a human for each sentence.
Common misconception
Self-supervised does not mean the model sets its own goals or evaluates itself. People still choose the data, objective, architecture, and training process.
Related terms
Sources
- Linus Ericsson and colleagues, “Self-Supervised Representation Learning: Introduction, Advances and Challenges”surveys methods that learn representations without manually annotated labels across several modalities.
Learn more
- Compare [[pretraining|Pretraining]], [[contrastive-learning|Contrastive Learning]], [[unsupervised-learning|Unsupervised Learning]], and [[training-data|Training Data]] to place Self-Supervised Learning in the surrounding system.
- Follow the cited source material above for the method, standard, or research context behind this draft.