Semi-Supervised Few-Shot Learning with MAMLDownload PDF

26 Jan 2018ICLR 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
4 Replies

Loading