DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models
This addresses memory efficiency and data privacy concerns for users and developers of large language models, representing an incremental improvement by combining existing techniques.
The paper tackles the problem of high memory costs and privacy risks in deploying large language models by introducing DP-MemArc, a training framework that reduces memory usage by about 2.5 times while ensuring robust differential privacy protection.
Large language models have repeatedly shown outstanding performance across diverse applications. However, deploying these models can inadvertently risk user privacy. The significant memory demands during training pose a major challenge in terms of resource consumption. This substantial size places a heavy load on memory resources, raising considerable practical concerns. In this paper, we introduce DP-MemArc, a novel training framework aimed at reducing the memory costs of large language models while emphasizing the protection of user data privacy. DP-MemArc incorporates side network or reversible network designs to support a variety of differential privacy memory-efficient fine-tuning schemes. Our approach not only achieves about 2.5 times in memory optimization but also ensures robust privacy protection, keeping user data secure and confidential. Extensive experiments have demonstrated that DP-MemArc effectively provides differential privacy-efficient fine-tuning across different task scenarios.