Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Semi-Supervised Few-Shot Learning with MAML
Rinu Boney, Alexander Ilin
Jan 26, 2018 (modified: Jan 26, 2018)ICLR 2018 Workshop Submissionreaders: everyone
Abstract:We present preliminary results on extending Model-Agnostic Meta-Learning (MAML) (Finn et al., 2017a) to fast adaptation to new classification tasks in the presence of unlabeled data. Using synthetic data, we show that MAML can adapt to new tasks without any labeled examples (unsupervised adaptation) when the new task has the same output space (classes) as the training tasks do. We further extend MAML to the semi-supervised few-shot learning scenario, when the output space of the new tasks can be different from the training tasks.
TL;DR:We present preliminary results on extending Model-Agnostic Meta-Learning (MAML) to fast adaptation to new classification tasks in the presence of unlabeled data.
Keywords:few-shot learning, meta learning, maml
Enter your feedback below and we'll get back to you as soon as possible.