In-Context Semi-Supervised Learning
By: Jiashuo Fan , Paul Rosu , Aaron T. Wang and more
There has been significant recent interest in understanding the capacity of Transformers for in-context learning (ICL), yet most theory focuses on supervised settings with explicitly labeled pairs. In practice, Transformers often perform well even when labels are sparse or absent, suggesting crucial structure within unlabeled contextual demonstrations. We introduce and study in-context semi-supervised learning (IC-SSL), where a small set of labeled examples is accompanied by many unlabeled points, and show that Transformers can leverage the unlabeled context to learn a robust, context-dependent representation. This representation enables accurate predictions and markedly improves performance in low-label regimes, offering foundational insights into how Transformers exploit unlabeled context for representation learning within the ICL framework.
Similar Papers
Can Transformers Break Encryption Schemes via In-Context Learning?
Machine Learning (CS)
Teaches computers to break secret codes.
A Simple Generalisation of the Implicit Dynamics of In-Context Learning
Machine Learning (CS)
Teaches computers to learn from examples without changing them.
Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study
Machine Learning (CS)
Teaches computers to learn better from examples.