提出新型低秩适配器聚合方法，降低联邦微调成本
Aggregating Low Rank Adapters in Federated Fine-tuning
- 设计新聚合策略优化联邦学习中低秩适配器的融合
- 在GLUE基准上实现比现有方法更高的模型性能
- 适合资源受限场景下的大模型高效微调
微调大型语言模型需要高昂的计算与内存开销，联邦数据训练时还需增加通信成本。因此，参数高效方法（PEFT）日益重要。低秩适配（LoRA）已在该领域取得良好效果。本文提出一种新型低秩适配器聚合方法，对比多种现有聚合方式，在联邦微调大型机器学习模型时，基于GLUE基准评估其性能表现。
原文摘要 · Abstract (English)
Fine-tuning large language models requires high computational and memory resources, and is therefore associated with significant costs. When training on federated datasets, an increased communication effort is also needed. For this reason, parameter-efficient methods (PEFT) are becoming increasingly important. In this context, very good results have already been achieved by fine-tuning with low-rank adaptation methods (LoRA). The application of LoRA methods in Federated Learning, and especially the aggregation of adaptation matrices, is a current research field. In this article, we propose a novel aggregation method and compare it with different existing aggregation methods of low rank adapters trained in a federated fine-tuning of large machine learning models and evaluate their performance with respect to selected GLUE benchmark datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。