Improving Generalization in Meta-learning via Task Augmentation

Understand

Meta-learning has proven to be a powerful paradigm for transferring the knowledge from previous tasks to facilitate the learning of a novel task.

• Current dominant algorithms train a well-generalized model initialization which is adapted to each task via the support set.
• The crux lies in optimizing the generalization capability of the initialization, which is measured by the performance of the adapted model on the query set of each task.
• Unfortunately, this generalization measure, evidenced by empirical results, pushes the initialization to overfit the meta-training tasks, which significantly impairs the generalization and adaptation to novel tasks.