Neural Routing in Meta Learning

TL;DR

This paper introduces neural routing in meta learning (NRML), a method that dynamically selects model parts based on input tasks using batch normalization scaling factors, improving few-shot classification performance.

Contribution

It proposes a novel task-dependent neuron selection approach in meta learning, inspired by neuroscience, to enhance model generalization and efficiency.

Findings

NRML outperforms existing meta learning baselines on few-shot classification.

Dynamic neuron selection improves model generalization.

Using BN scaling factors enables effective task-dependent routing.

Abstract

Meta-learning often referred to as learning-to-learn is a promising notion raised to mimic human learning by exploiting the knowledge of prior tasks but being able to adapt quickly to novel tasks. A plethora of models has emerged in this context and improved the learning efficiency, robustness, etc. The question that arises here is can we emulate other aspects of human learning and incorporate them into the existing meta learning algorithms? Inspired by the widely recognized finding in neuroscience that distinct parts of the brain are highly specialized for different types of tasks, we aim to improve the model performance of the current meta learning algorithms by selectively using only parts of the model conditioned on the input tasks. In this work, we describe an approach that investigates task-dependent dynamic neuron selection in deep convolutional neural networks (CNNs) by leveraging the scaling factor in the batch normalization (BN) layer associated with each convolutional layer. The problem is intriguing because the idea of helping different parts of the model to learn from different types of tasks may help us train better filters in CNNs, and improve the model generalization performance. We find that the proposed approach, neural routing in meta learning (NRML), outperforms one of the well-known existing meta learning baselines on few-shot classification tasks on the most widely used benchmark datasets.