Release the Potential of Memory Buffer in Continual Learning: A Dynamic System Perspective
Wang, Zhenyi Shen, Li Duan, Tiehang Zhu, Yanjun Liu, Tongliang Gao, Mingchen Tao, Dacheng
Wang, Zhenyi
Shen, Li
Duan, Tiehang
Zhu, Yanjun
Liu, Tongliang
Gao, Mingchen
Tao, Dacheng
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Continual learning (CL) focuses on learning non-stationary data distribution without forgetting previous knowledge. The most widely used memory-replay approaches are often prone to memory overfitting due to the limited memory diversity and hardness. Existing work mitigating memory overfitting either lacks data diversity or hardness or is hard to train. To address the above limitations and release the memory buffer potential, we view the memory buffer transformation from a new dynamic system perspective and propose a continuous and reversible memory transformation method. We introduce an adversarial optimization objective that jointly learns the CL model and memory transformer. Specifically, we present a deterministic continuous memory transformer (DCMT) to generate diverse memory data. Furthermore, we inject uncertainty into the transformation function and develop a stochastic continuous memory transformer (SCMT), which substantially enhances the diversity of the transformed memory buffer. The presented neural transformation approaches have significant advantages over existing ones: (1) they significantly increase the memory buffer diversity and hardness to overfit; (2) they are memory efficient without needing to make a replica of the memory data. Extensive experiments show a significant improvement with our approach compared to strong baselines.
Citation
Z. Wang, L. Shen, T. Duan, Y. Zhu, T. Liu, M. Gao, D. Tao, "Release the Potential of Memory Buffer in Continual Learning: A Dynamic System Perspective," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 48, no. 2, pp. 1811-1824, 2025, https://doi.org/10.1109/tpami.2025.3619883.
Source
IEEE Transactions on Pattern Analysis and Machine Intelligence
Conference
Keywords
46 Information and Computing Sciences, 4611 Machine Learning
Subjects
Source
Publisher
IEEE