Assessor-guided learning for continual environments.

Muhammad Anwar Ma'sum, Mahardhika Pratama, Edwin Lughofer, Weiping Ding, Wisnu Jatmiko

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)

Abstract

This paper proposes an assessor-guided learning strategy for continual learning where an assessor guides the learning process of a base learner by controlling the direction and pace of the learning process thus allowing an efficient learning of new environments while protecting against the catastrophic interference problem. The assessor is trained in a meta-learning manner with a meta-objective to boost the learning process of the base learner. It performs a soft-weighting mechanism of every sample accepting positive samples while rejecting negative samples. The training objective of a base learner is to minimize a meta-weighted combination of the cross entropy loss function, the dark experience replay (DER) loss function and the knowledge distillation loss function whose interactions are controlled in such a way to attain an improved performance. A compensated over-sampling (COS) strategy is developed to overcome the class imbalanced problem of the episodic memory due to limited memory budgets. Our approach, Assessor-Guided Learning Approach (AGLA), has been evaluated in the class-incremental and task-incremental learning problems. AGLA achieves improved performances compared to its competitors while the theoretical analysis of the COS strategy is offered.
Original languageUndefined/Unknown
Article number119088
Number of pages1
JournalInf. Sci.
Volume640
DOIs
Publication statusPublished - 2023

Keywords

  • Continual learning
  • Incremental learning
  • Lifelong learning
  • Meta-learning

Cite this