A Simple Neural Attentive Meta-Learner

TLDR

Deep neural networks excel with abundant data but struggle with scarce data or rapid adaptation; meta‑learning addresses this by training on a distribution of related tasks, yet many existing methods are hand‑designed and constrained. The authors propose a simple, generic meta‑learner that combines temporal convolutions for aggregating past experience with soft attention to focus on relevant information. They evaluate the Simple Neural Attentive Learner on a broad set of benchmarked supervised and reinforcement learning tasks. SNAIL achieves state‑of‑the‑art performance on all tasks, surpassing prior methods by significant margins.

Abstract

Deep neural networks excel in regimes with large amounts of data, but tend to struggle when data is scarce or when they need to adapt quickly to changes in the task. In response, recent work in meta-learning proposes training a meta-learner on a distribution of similar tasks, in the hopes of generalization to novel but related tasks by learning a high-level strategy that captures the essence of the problem it is asked to solve. However, many recent meta-learning approaches are extensively hand-designed, either using architectures specialized to a particular application, or hard-coding algorithmic components that constrain how the meta-learner solves the task. We propose a class of simple and generic meta-learner architectures that use a novel combination of temporal convolutions and soft attention; the former to aggregate information from past experience and the latter to pinpoint specific pieces of information. In the most extensive set of meta-learning experiments to date, we evaluate the resulting Simple Neural AttentIve Learner (or SNAIL) on several heavily-benchmarked tasks. On all tasks, in both supervised and reinforcement learning, SNAIL attains state-of-the-art performance by significant margins.