Meta-Meta Classification for One-Shot Learning
This addresses few-shot learning challenges for AI systems needing adaptation with minimal data, but appears incremental as it builds on existing meta-learning and ensembling concepts.
The paper tackles the problem of learning in small-data settings by proposing meta-meta classification, which uses an ensemble of specialized learners combined by a meta-meta classifier to solve few-shot tasks, and shows it outperforms traditional meta-learning and ensembling approaches on a one-shot classification task.
We present a new approach, called meta-meta classification, to learning in small-data settings. In this approach, one uses a large set of learning problems to design an ensemble of learners, where each learner has high bias and low variance and is skilled at solving a specific type of learning problem. The meta-meta classifier learns how to examine a given learning problem and combine the various learners to solve the problem. The meta-meta learning approach is especially suited to solving few-shot learning tasks, as it is easier to learn to classify a new learning problem with little data than it is to apply a learning algorithm to a small data set. We evaluate the approach on a one-shot, one-class-versus-all classification task and show that it is able to outperform traditional meta-learning as well as ensembling approaches.