SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs
This work addresses the challenge of scalable and resource-efficient continual learning for LLMs, offering an incremental improvement over existing prompt tuning methods.
The paper tackles the problem of efficient continual learning in large language models by proposing SPARC, a lightweight framework that uses PCA-based prompt tuning in a lower-dimensional space, achieving high knowledge retention with only 0.04% to 1% of parameters tuned and improved accuracy on benchmarks like SuperGLUE.
We propose SPARC, a lightweight continual learning framework for large language models (LLMs) that enables efficient task adaptation through prompt tuning in a lower-dimensional space. By leveraging principal component analysis (PCA), we identify a compact subspace of the training data. Optimizing prompts in this lower-dimensional space enhances training efficiency, as it focuses updates on the most relevant features while reducing computational overhead. Furthermore, since the model's internal structure remains unaltered, the extensive knowledge gained from pretraining is fully preserved, ensuring that previously learned information is not compromised during adaptation. Our method achieves high knowledge retention in both task-incremental and domain-incremental continual learning setups while fine-tuning only 0.04% of the model's parameters. Additionally, by integrating LoRA, we enhance adaptability to computational constraints, allowing for a tradeoff between accuracy and training cost. Experiments on the SuperGLUE benchmark demonstrate that our PCA-based prompt tuning combined with LoRA maintains full knowledge retention while improving accuracy, utilizing only 1% of the model's parameters. These results establish our approach as a scalable and resource-efficient solution for continual learning in LLMs.