A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems

TL;DR

This paper introduces a domain-agnostic evaluation framework with metrics for assessing Lifelong Learning systems, addressing robustness, transfer, and scalability in real-world scenarios through multiple case studies.

Contribution

It proposes a holistic, domain-agnostic suite of metrics and an evaluation framework for Lifelong Learning systems, unifying assessment of multiple capabilities.

Findings

Metrics inform development of complex Lifelong Learning systems

Quantifies trade-offs like Stability-Plasticity and Sample Efficiency-Robustness

Framework guides future progress assessment

Abstract

Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed. This critical gap may be addressed through the development of "Lifelong Learning" systems that are capable of 1) Continuous Learning, 2) Transfer and Adaptation, and 3) Scalability. Unfortunately, efforts to improve these capabilities are typically treated as distinct areas of research that are assessed independently, without regard to the impact of each separate capability on other aspects of the system. We instead propose a holistic approach, using a suite of metrics and an evaluation framework to assess Lifelong Learning in a principled way that is agnostic to specific domains or system techniques. Through five case studies, we show that this suite of metrics can inform the development of varied and complex Lifelong Learning systems. We highlight how the proposed suite of metrics quantifies performance trade-offs present during Lifelong Learning system development - both the widely discussed Stability-Plasticity dilemma and the newly proposed relationship between Sample Efficient and Robust Learning. Further, we make recommendations for the formulation and use of metrics to guide the continuing development of Lifelong Learning systems and assess their progress in the future.