- TL;DR: A novel meta-learning method is introduced where a meta-learner learns to optimize a learner's weight updates by optimizing the input and output to and from each node in the learner network.
- Abstract: Meta-learning is an exciting and powerful paradigm that aims to improve the effectiveness of current learning systems. By formulating the learning process as an optimization problem, a model can learn how to learn while requiring significantly less data or experience than traditional approaches. Gradient-based meta-learning methods aims to do just that, however recent work have shown that the effectiveness of these approaches are primarily due to feature reuse and very little has to do with priming the system for rapid learning (learning to make effective weight updates on unseen data distributions). This work introduces Nodal Optimization for Recurrent Meta-Learning (NORML), a novel meta-learning framework where an LSTM-based meta-learner performs neuron-wise optimization on a learner for efficient task learning. Crucially, the number of meta-learner parameters needed in NORML, increases linearly relative to the number of learner parameters. Allowing NORML to potentially scale to learner networks with very large numbers of parameters. While NORML also benefits from feature reuse it is shown experimentally that the meta-learner LSTM learns to make effective weight updates using information from previous data-points and update steps.
- Keywords: meta-learning, learning to learn, few-shot classification, memory-based optimization
- Original Pdf: pdf