Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Aggregating Low Rank Adapters in Federated Fine-tuning

About

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.

Evelyn Trautmann, Ian Hales, Martin F. Volk• 2025

Related benchmarks

TaskDatasetResultRank
Natural Language InferenceMNLI--
80
Sentiment AnalysisSST2
Accuracy94.9541
47
Natural Language UnderstandingGLUE (imbalanced partition)
SST-2 Accuracy92.7752
4
Showing 3 of 3 rows

Other info

Follow for update