.png){kind=icon}
Return
Joint Memory Optimization for Continual Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TCSVT.2025.3539661.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Continual learning, focusing on sequential knowledge acquisition and retention, necessitates efficient memory management. This paper introduces a holistic approach, diverging from traditional methods that separately optimize neural network and replay buffer memory. We aim to enhance overall memory efficiency, addressing neural network parameters and replay buffer concurrently within strict memory constraints. This is achieved by harnessing neural network parameter redundancies and employing compression techniques like pruning and quantization, allowing data replay storage without extra memory overhead. Balancing memory use across components is challenging due to the complex search space of combined tasks. We tackle this by conceptualizing it as a bi-level optimization problem, integrating all tasks under a single objective, thus optimizing memory use and managing the interplay between different components. We employ a synergy of optimization techniques to solve this challenging bi-level optimization problem. Our experimental findings affirm the superior performance of our proposed method, outperforming existing techniques such as prompt-based, feature-replay, exemplar-replay, and regularization-based methods under stringent memory constraints, consistently across various datasets and neural network architectures.
Keywords:
Continual learning
model compression
Journal
IF:
11.1
Papers:
873
Citations:
3.1W
Organization
Cited Papers
.png){kind=icon}
ShareSaveCODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning
OAAI
OAAIShareSaveShareSaveShareSaveShareSaveShareSave
View more