Continual Learning in the Presence of Repetition

arXiv:2405.04101v1 Announce Type: new
Abstract: Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world problems, the concept of repetition in the data stream is not often considered in standard benchmarks for CL. Unlike with the rehearsal mechanism in buffer-based strategies, where sample repetition is controlled by the strategy, repetition in the data stream naturally stems from the environment. This report provides a summary of the …

abstract arxiv benchmarks concept continual cs.ai cs.lg data data stream environments ever framework objects real-world problems standard tasks training training models type world