Abstract Deep Neural Networks (or DNNs) must constantly cope with distribution changes in
the input data when the task of interest or the data collection protocol changes. Retraining a …

Humans can often quickly and efficiently solve complex new learning tasks given only a
small set of examples. In contrast, modern artificially intelligent systems often require …

Meta-learning has emerged as a new paradigm in AI to challenge the limitation of
conventional deep learning to acquire only task-specific knowledge. Meta-learning …

To benefit the learning of a new task, meta-learning has been proposed to transfer a well-
generalized meta-model learned from various meta-training tasks. Existing meta-learning …

Existing meta-learning works assume that each task has available training and testing data.
However, there are many available pre-trained models without accessing their training data …

Deep neural networks can yield good performance on various tasks but often require large
amounts of data to train them. Meta-learning received considerable attention as one …

Model agnostic meta-learning (MAML) is a popular state-of-the-art meta-learning algorithm
that provides good weight initialization of a model given a variety of learning tasks. The …

Inspired by optimization techniques, we propose a novel meta-learning algorithm with
gradient modulation to encourage fast-adaptation of neural networks in the absence of …

Meta-learning enables models to adapt to new environments rapidly with a few training
examples. Current gradient-based meta-learning methods concentrate on finding good …

Meta-learning aims to learn general knowledge with diverse training tasks conducted from
limited data, and then transfer it to new tasks. It is commonly believed that increasing task …