MetaFun: Meta-Learning with Iterative Functional Updates
This addresses the problem of few-shot learning for AI systems by providing a novel approach that improves accuracy on large-scale benchmarks, though it is incremental in building on encoder-decoder meta-learning methods.
The paper tackled few-shot classification by developing a meta-learning method that encodes data into an infinite-dimensional functional representation using iterative updates, achieving state-of-the-art performance on benchmarks like miniImageNet and tieredImageNet.
We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one. Furthermore, rather than directly producing the representation, we learn a neural update rule resembling functional gradient descent which iteratively improves the representation. The final representation is used to condition the decoder to make predictions on unlabeled data. Our approach is the first to demonstrates the success of encoder-decoder style meta-learning methods like conditional neural processes on large-scale few-shot classification benchmarks such as miniImageNet and tieredImageNet, where it achieves state-of-the-art performance.