Continuous-Time Meta-Learning with Forward Mode Differentiation
This addresses the challenge of flexible and memory-efficient meta-learning for few-shot learning, though it is incremental as it builds on existing gradient-based meta-learning methods.
The paper tackles the problem of meta-learning by proposing Continuous-Time Meta-Learning (COMLN), which models adaptation as a continuous ODE instead of discrete gradient steps, enabling optimization of adaptation length and efficient memory usage via forward mode differentiation, achieving competitive performance on few-shot image classification tasks.
Drawing inspiration from gradient-based meta-learning methods with infinitely small gradient steps, we introduce Continuous-Time Meta-Learning (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector field. Specifically, representations of the inputs are meta-learned such that a task-specific linear classifier is obtained as a solution of an ordinary differential equation (ODE). Treating the learning process as an ODE offers the notable advantage that the length of the trajectory is now continuous, as opposed to a fixed and discrete number of gradient steps. As a consequence, we can optimize the amount of adaptation necessary to solve a new task using stochastic gradient descent, in addition to learning the initial conditions as is standard practice in gradient-based meta-learning. Importantly, in order to compute the exact meta-gradients required for the outer-loop updates, we devise an efficient algorithm based on forward mode differentiation, whose memory requirements do not scale with the length of the learning trajectory, thus allowing longer adaptation in constant memory. We provide analytical guarantees for the stability of COMLN, we show empirically its efficiency in terms of runtime and memory usage, and we illustrate its effectiveness on a range of few-shot image classification problems.