A Lazy Approach to Long-Horizon Gradient-Based Meta-Learning

Gradient-based meta-learning relates task-specific models to a meta-model by gradients. By this design, an algorithm first optimizes the task-specific models by an inner loop and then backpropagates meta-gradients through the loop to update the meta-model. The number of inner-loop optimization steps has to be small (e.g., one step) to avoid high-order derivatives, big memory footprints, and the risk of vanishing or exploding meta-gradients. We propose an intuitive teacher-student scheme to enable the gradient-based meta-learning algorithms to explore long horizons by the inner loop. The key idea is to employ a student network to explore the search space of task-specific models adequately (e.g., by more than ten steps), and a teacher then takes a ``leap'' toward the regions probed by the student. The teacher not only arrives at a high-quality model but also defines a lightweight computation graph for meta-gradients. Our approach is generic, as we verify its effectiveness with four meta-learning algorithms over three tasks: few-shot learning, long-tailed classification, and meta-attack.