Understanding Continual Learning Settings with Data Distribution Drift Analysis

TL;DR

This paper categorizes different types of data distribution drifts in continual learning, providing a framework to better understand and define the challenges posed by non-stationary data environments.

Contribution

It introduces a formal framework for representing and analyzing data distribution drifts in continual learning scenarios, clarifying terminology and assumptions.

Findings

Categorizes types of context drifts in continual learning.

Provides a formal framework for data distribution drift analysis.

Clarifies terminology and assumptions in the field.

Abstract

Classical machine learning algorithms often assume that the data are drawn i.i.d. from a stationary probability distribution. Recently, continual learning emerged as a rapidly growing area of machine learning where this assumption is relaxed, i.e. where the data distribution is non-stationary and changes over time. This paper represents the state of data distribution by a context variable $c$. A drift in $c$ leads to a data distribution drift. A context drift may change the target distribution, the input distribution, or both. Moreover, distribution drifts might be abrupt or gradual. In continual learning, context drifts may interfere with the learning process and erase previously learned knowledge; thus, continual learning algorithms must include specialized mechanisms to deal with such drifts. In this paper, we aim to identify and categorize different types of context drifts and potential assumptions about them, to better characterize various continual-learning scenarios. Moreover, we propose to use the distribution drift framework to provide more precise definitions of several terms commonly used in the continual learning field.