Understanding Continual Learning Settings with Data Distribution Drift Analysis
This work addresses the challenge of understanding and formalizing distribution drifts for researchers in continual learning, but it is incremental as it focuses on categorization and definitions rather than new algorithms.
The paper tackles the problem of characterizing data distribution drifts in continual learning, where non-stationary data can erase learned knowledge, by identifying and categorizing types of context drifts and providing precise definitions for continual learning terms.
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.