English

FDAPT: Federated Domain-adaptive Pre-training for Language Models

Machine Learning 2023-11-10 v2 Artificial Intelligence Distributed, Parallel, and Cluster Computing

Abstract

Foundation models (FMs) have shown prominent success in a wide range of tasks. Their applicability to specific domain-task pairings relies on the availability of, both, high-quality data and significant computational resources. These challenges are not new to the field and, indeed, Federated Learning (FL) has been shown to be a promising solution in similar setups. This paper tackles the specific case of Domain-Adaptive Pre-Training (DAPT), a key step in the application of FMs. We conduct the first comprehensive empirical study to evaluate the performance of Federated Domain-Adaptive Pre-Training (FDAPT). We demonstrate that FDAPT can maintain competitive downstream task performance to the centralized baseline in both IID and non-IID situations. Finally, we propose a novel algorithm, Frozen Federated Domain-Adaptive Pre-Training (FFDAPT). FFDAPT improves the computational efficiency by 12.1% on average and exhibits similar downstream task performance to vanilla FDAPT, with general performance fluctuations remaining less than 1%.

Keywords

Cite

@article{arxiv.2307.06933,
  title  = {FDAPT: Federated Domain-adaptive Pre-training for Language Models},
  author = {Lekang Jiang and Filip Svoboda and Nicholas D. Lane},
  journal= {arXiv preprint arXiv:2307.06933},
  year   = {2023}
}

Comments

Accepted at International Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS 2023

R2 v1 2026-06-28T11:29:42.399Z