Abstract
We explore on-device self-supervised collaborative fine-tuning of large language models with limited local data availability. Taking inspiration from the collaborative learning community, we introduce three distinct trust-weighted gradient aggregation schemes: weight similarity-based, prediction similarity-based and validation performance-based. To minimize communication overhead, we integrate Low-Rank Adaptation (LoRA) and only exchange LoRA weight updates. Our protocols, driven by prediction and performance metrics, surpass both FedAvg and local fine-tuning methods, which is particularly evident in realistic scenarios with more diverse local data distributions. The results underscore the effectiveness of our approach in addressing heterogeneity and scarcity within local datasets.
Abstract (translated)
我们研究了在有限本地数据可用性下对大型语言模型的自监督协同微调。从协同学习社区中汲取灵感，我们引入了三种不同的信任加权梯度聚合方案：基于权重相似度的、基于预测相似度的和基于验证性能的。为了最小化通信开销，我们集成了 Low-Rank Adaptation（LoRA），并且只交换 LoRA 权重更新。我们的协议，由预测和性能指标驱动，超越了 FedAvg 和局部微调方法，尤其是在具有更丰富本地数据分布的现实场景中，这种效果尤为明显。结果证实了我们在解决局部数据异质性和稀疏性问题方面的方法的有效性。
URL
https://arxiv.org/abs/2404.09753
