FL-TAC: Enhanced Fine-Tuning in Federated Learning via Low-Rank, Task-Specific Adapter Clustering

arXiv:2404.15384v1 Announce Type: new
Abstract: Although large-scale pre-trained models hold great potential for adapting to downstream tasks through fine-tuning, the performance of such fine-tuned models is often limited by the difficulty of collecting sufficient high-quality, task-specific data. Federated Learning (FL) offers a promising solution by enabling fine-tuning across large-scale clients with a variety of task data, but it is bottlenecked by significant communication overhead due to the pre-trained models' extensive size. This paper addresses the high communication cost for fine-tuning …

abstract adapter arxiv clustering cs.ai cs.lg data enabling federated learning fine-tuning low performance pre-trained models quality scale solution tasks through type via