Algorithm Design for Online Meta-Learning with Task Boundary Detection

TL;DR

This paper introduces a novel task-agnostic online meta-learning algorithm capable of detecting task switches and distribution shifts in non-stationary environments, enabling quick adaptation without storing past data.

Contribution

It proposes effective detection mechanisms for task changes and distribution shifts, and develops an online meta-learning algorithm that updates solely based on current data, achieving sublinear regret.

Findings

Significant performance improvements over baseline methods on three benchmarks.

Effective detection of task switches and distribution shifts.

Achieved sublinear task-averaged regret under mild conditions.

Abstract

Online meta-learning has recently emerged as a marriage between batch meta-learning and online learning, for achieving the capability of quick adaptation on new tasks in a lifelong manner. However, most existing approaches focus on the restrictive setting where the distribution of the online tasks remains fixed with known task boundaries. In this work, we relax these assumptions and propose a novel algorithm for task-agnostic online meta-learning in non-stationary environments. More specifically, we first propose two simple but effective detection mechanisms of task switches and distribution shift based on empirical observations, which serve as a key building block for more elegant online model updates in our algorithm: the task switch detection mechanism allows reusing of the best model available for the current task at hand, and the distribution shift detection mechanism differentiates the meta model update in order to preserve the knowledge for in-distribution tasks and quickly learn the new knowledge for out-of-distribution tasks. In particular, our online meta model updates are based only on the current data, which eliminates the need of storing previous data as required in most existing methods. We further show that a sublinear task-averaged regret can be achieved for our algorithm under mild conditions. Empirical studies on three different benchmarks clearly demonstrate the significant advantage of our algorithm over related baseline approaches.