A Practical Guide to Streaming Continual Learning
This work addresses the need for hybrid approaches in real-world applications where agents must handle non-stationary data streams, though it is incremental in nature.
The paper tackles the problem of combining rapid adaptation and knowledge retention in machine learning by proposing Streaming Continual Learning (SCL) as a unifying paradigm, showing through experiments that existing CL and SML methods alone struggle to achieve both goals effectively.
Continual Learning (CL) and Streaming Machine Learning (SML) study the ability of agents to learn from a stream of non-stationary data. Despite sharing some similarities, they address different and complementary challenges. While SML focuses on rapid adaptation after changes (concept drifts), CL aims to retain past knowledge when learning new tasks. After a brief introduction to CL and SML, we discuss Streaming Continual Learning (SCL), an emerging paradigm providing a unifying solution to real-world problems, which may require both SML and CL abilities. We claim that SCL can i) connect the CL and SML communities, motivating their work towards the same goal, and ii) foster the design of hybrid approaches that can quickly adapt to new information (as in SML) without forgetting previous knowledge (as in CL). We conclude the paper with a motivating example and a set of experiments, highlighting the need for SCL by showing how CL and SML alone struggle in achieving rapid adaptation and knowledge retention.