Meta-Learning with Adaptive Hyperparameters

The ability to quickly learn and generalize from only few examples is an essential goal of few-shot learning. Gradient-based meta-learning algorithms effectively tackle the problem by learning how to learn novel tasks. In particular, modelagnostic meta-learning (MAML) encodes the prior knowledge into a trainable initialization, which allowed for fast adaptation to few examples. Despite its popularity, several recent works question the effectiveness of MAML initialization especially when test tasks are different from training tasks, thus suggesting various methodologies to improve the initialization. Instead of searching for a better initialization, we focus on a complementary factor in MAML framework, the inner-loop optimization (or fast adaptation). Consequently, we propose a new weight update rule that greatly enhances the fast adaptation process. Specifically, we introduce a small meta-network that can adaptively generate per-step hyperparameters: learning rate and weight decay coefficients. The experimental results validate that the Adaptive Learning of hyperparameters for Fast Adaptation (ALFA) is the equally important ingredient that was often neglected in the recent few-shot learning approaches. Surprisingly, fast adaptation from random initialization with ALFA can already outperform MAML.