Lifelong Machine Learning Systems: Beyond Learning Algorithms

TLDR

Lifelong Machine Learning (LML) studies systems that acquire multiple tasks across domains throughout their lifetime. The authors aim to retain and transfer knowledge sequentially in LML systems, advocating a shift from algorithmic focus to system-level design and outlining future research directions. They define LML, introduce a comprehensive reference framework covering all machine learning forms, and enumerate key challenges and benefits for future research. They present arguments supporting their stance and address possible counterpoints.

Abstract

Lifelong Machine Learning, or LML, considers systems that can learn many tasks from one or more domains over its lifetime. The goal is to sequentially retain learned knowledge and to selectively transfer that knowledge when learning a new task so as to develop more accurate hypotheses or policies. Following a review of prior work on LML, we propose that it is now appropriate for the AI community to move beyond learning algorithms to more seriously consider the nature of systems that are capable of learning over a lifetime. Reasons for our position are presented and potential counter-arguments are discussed. The remainder of the paper contributes by defining LML, presenting a reference framework that considers all forms of machine learning, and listing several key challenges for and benefits from LML research. We conclude with ideas for next steps to advance the field.