paper-with-me

홈 › Papers

Scaling Federated Learning for Fine-tuning of Large Language Models

2021-02-01 · Agrin Hilmkil, Sebastian Callh, Matteo Barbieri, Leon René Sütfeld, Edvin Listo Zec, Olof Mogren

Federated learning (FL) is a promising approach to distributed compute, as well as distributed data, and provides a level of privacy and compliance to legal frameworks. This makes FL attractive for both consumer and healthcare applications. While the area is actively being explored, few studies have examined FL in the context of larger language models and there is a lack of comprehensive reviews of robustness across tasks, architectures, numbers of clients, and other relevant factors. In this paper, we explore the fine-tuning of Transformer-based language models in a federated learning setting. We evaluate three popular BERT-variants of different sizes (BERT, ALBERT, and DistilBERT) on a number of text classification tasks such as sentiment analysis and author identification. We perform an extensive sweep over the number of clients, ranging up to 32, to evaluate the impact of distributed compute on task performance in the federated averaging setting. While our findings suggest that the large sizes of the evaluated models are not generally prohibitive to federated training, we found that the different models handle federated averaging to a varying degree. Most notably, DistilBERT converges significantly slower with larger numbers of clients, and under some circumstances, even collapses to chance level performance. Investigating this issue presents an interesting perspective for future research.

📄 PDF Abstract BibTeX arXiv:2102.00875

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningSentiment Analysistext-classificationText Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
BERT BERT, or Bidirectional Encoder Representations from Transformers, improves upon standard Transformers by removing the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Stabilized Fine-Tuning with LoRA in Federated Learning: Mitigating the Side Effect of Client Size and Rank via the Scaling Factor

2026-03-09 · Jiayu Huang, Xiaohu Wu, Tiantian He, Qicheng Lao arxiv

Large Language Models (LLMs) are pivotal in natural language processing. The impracticality of full fine-tuning has prompted Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA), optimizing low-…

parameter-efficient fine-tuningFederated Learning

Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning

2025-06-05 · Arian Raje, Baris Askin, Divyansh Jhunjhunwala, Gauri Joshi

Large language models (LLMs) have not yet effectively leveraged the vast amounts of edge-device data, and federated learning (FL) offers a promising paradigm to collaboratively fine-tune LLMs without transferring private…

Federated Learning

Conflict-Aware Federated Fine-Tuning of Large Language Models with Mixture-of-Experts

2026-06-14 · Yijun Lu, Zihan Fang, Pengpeng Qiao, Zheng Lin 외 arxiv

The continuous scaling of large language models (LLMs) incurs prohibitive computational costs, making Mixture-of-Experts (MoE) a scalable alternative for efficient fine-tuning via sparse activation. While federated learn…

Federated Learning

Beyond Parameter Aggregation: Semantic Consensus for Federated Fine-Tuning of LLMs

2026-05-12 · Amr Abourayya, Jens Kleesiek, Michael Kamp arxiv

Federated fine-tuning of large language models is commonly formulated as a parameter aggregation problem. However, even parameter-efficient methods require transmitting large collections of trainable weights, assume alig…

Text Generation

FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations

2024-09-09 · Ziyao Wang, Zheyu Shen, Yexiao He, Guoheng Sun 외

The rapid development of Large Language Models (LLMs) has been pivotal in advancing AI, with pre-trained LLMs being adaptable to diverse downstream tasks through fine-tuning. Federated learning (FL) further enhances fine…

Federated LearningPrivacy Preserving