Compositional meta-learning through probabilistic task inference
This addresses the challenge of data-efficient knowledge reuse across tasks for AI systems, though it appears incremental as it combines existing neural and probabilistic approaches.
The paper tackles the problem of meta-learning by proposing a compositional model that represents tasks as structured combinations of reusable computations, achieving rapid inference of new solutions from single examples without parameter updates.
To solve a new task from minimal experience, it is essential to effectively reuse knowledge from previous tasks, a problem known as meta-learning. Compositional solutions, where common elements of computation are flexibly recombined into new configurations, are particularly well-suited for meta-learning. Here, we propose a compositional meta-learning model that explicitly represents tasks as structured combinations of reusable computations. We achieve this by learning a generative model that captures the underlying components and their statistics shared across a family of tasks. This approach transforms learning a new task into a probabilistic inference problem, which allows for finding solutions without parameter updates through highly constrained hypothesis testing. Our model successfully recovers ground truth components and statistics in rule learning and motor learning tasks. We then demonstrate its ability to quickly infer new solutions from just single examples. Together, our framework joins the expressivity of neural networks with the data-efficiency of probabilistic inference to achieve rapid compositional meta-learning.