Streaming Continual Learning for Unified Adaptive Intelligence in Dynamic Environments

TL;DR

This paper introduces Streaming Continual Learning (SCL), a unified framework combining Continual Learning and Streaming Machine Learning to enable models to adapt to evolving data streams without forgetting prior knowledge.

Contribution

It proposes a new unified setting called SCL that extends existing CL and SML techniques, fostering collaboration between the two fields for adaptive intelligence.

Findings

SCL unifies CL and SML frameworks.

Highlights the importance of bridging CL and SML communities.

Emphasizes the potential of SCL for dynamic environments.

Abstract

Developing effective predictive models becomes challenging in dynamic environments that continuously produce data and constantly change. Continual Learning (CL) and Streaming Machine Learning (SML) are two research areas that tackle this arduous task. We put forward a unified setting that harnesses the benefits of both CL and SML: their ability to quickly adapt to non-stationary data streams without forgetting previous knowledge. We refer to this setting as Streaming Continual Learning (SCL). SCL does not replace either CL or SML. Instead, it extends the techniques and approaches considered by both fields. We start by briefly describing CL and SML and unifying the languages of the two frameworks. We then present the key features of SCL. We finally highlight the importance of bridging the two communities to advance the field of intelligent systems.