Class-Incremental Experience Replay for Continual Learning under Concept Drift
This addresses the need for machine learning systems to manage constantly changing data, offering a unified solution for researchers and practitioners in continual learning and data stream mining, though it appears incremental as it combines existing ideas.
The paper tackles the problem of unifying continual learning and data stream mining by proposing a novel approach that handles both accumulating knowledge and adapting to concept drift, achieving a holistic framework for learning from dynamic data.
Modern machine learning systems need to be able to cope with constantly arriving and changing data. Two main areas of research dealing with such scenarios are continual learning and data stream mining. Continual learning focuses on accumulating knowledge and avoiding forgetting, assuming information once learned should be stored. Data stream mining focuses on adaptation to concept drift and discarding outdated information, assuming that only the most recent data is relevant. While these two areas are mainly being developed in separation, they offer complementary views on the problem of learning from dynamic data. There is a need for unifying them, by offering architectures capable of both learning and storing new information, as well as revisiting and adapting to changes in previously seen concepts. We propose a novel continual learning approach that can handle both tasks. Our experience replay method is fueled by a centroid-driven memory storing diverse instances of incrementally arriving classes. This is enhanced with a reactive subspace buffer that tracks concept drift occurrences in previously seen classes and adapts clusters accordingly. The proposed architecture is thus capable of both remembering valid and forgetting outdated information, offering a holistic framework for continual learning under concept drift.