Generalising via Meta-Examples for Continual Learning in the Wild

TL;DR

This paper introduces FUSION, a novel meta-learning approach for continual learning from unlabelled and scarce data streams, combining unsupervised, continual, and few-shot learning to improve adaptability and knowledge retention.

Contribution

The paper proposes MEML, a meta-example meta-learning method with self-attention, and extends it with augmented surrogate tasks to enhance generalisation in continual, few-shot, and unsupervised learning scenarios.

Findings

FUSION outperforms state-of-the-art methods on vision benchmarks.

MEML effectively consolidates meta-representations with self-attention.

Augmented surrogate tasks improve generalisation from limited data.

Abstract

Future deep learning systems call for techniques that can deal with the evolving nature of temporal data and scarcity of annotations when new problems occur. As a step towards this goal, we present FUSION (Few-shot UnSupervIsed cONtinual learning), a learning strategy that enables a neural network to learn quickly and continually on streams of unlabelled data and unbalanced tasks. The objective is to maximise the knowledge extracted from the unlabelled data stream (unsupervised), favor the forward transfer of previously learnt tasks and features (continual) and exploit as much as possible the supervised information when available (few-shot). The core of FUSION is MEML - Meta-Example Meta-Learning - that consolidates a meta-representation through the use of a self-attention mechanism during a single inner loop in the meta-optimisation stage. To further enhance the capability of MEML to generalise from few data, we extend it by creating various augmented surrogate tasks and by optimising over the hardest. An extensive experimental evaluation on public computer vision benchmarks shows that FUSION outperforms existing state-of-the-art solutions both in the few-shot and continual learning experimental settings.