Task Agnostic Continual Learning via Meta Learning

TL;DR

This paper introduces a task-agnostic continual learning framework that leverages meta-learning to enable neural networks to quickly adapt and recover performance without prior knowledge of task boundaries, addressing catastrophic forgetting.

Contribution

It proposes a novel meta-learning based approach for continual learning that does not require task boundary information, separating task-specific and task-agnostic parameters for improved adaptability.

Findings

Framework enables faster recovery of performance after task switches.

Meta-learning enhances continual learning without explicit task boundary knowledge.

Applicable to supervised learning scenarios with promising results.

Abstract

While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that studies learning under non-stationary distribution is provided by continual learning, where the non-stationarity is imposed by a sequence of distinct tasks. Most methods in this space assume, however, the knowledge of task boundaries, and focus on alleviating catastrophic forgetting. In this work, we depart from this view and move the focus towards faster remembering -- i.e measuring how quickly the network recovers performance rather than measuring the network's performance without any adaptation. We argue that in many settings this can be more effective and that it opens the door to combining meta-learning and continual learning techniques, leveraging their complementary advantages. We propose a framework specific for the scenario where no information about task boundaries or task identity is given. It relies on a separation of concerns into what task is being solved and how the task should be solved. This framework is implemented by differentiating task specific parameters from task agnostic parameters, where the latter are optimized in a continual meta learning fashion, without access to multiple tasks at the same time. We showcase this framework in a supervised learning scenario and discuss the implication of the proposed formalism.