Scalable Multi-Domain Adaptation of Language Models using Modular Experts
Keywords: domain adaptation, mixture of experts, MoE, fine-tuning, large language models, sharding
TL;DR: Improve LLM performance on multi-domain datasets using modular, domain-specialized experts.
Abstract: Domain-specific adaptation is critical to maximizing the performance of pre-trained
language models (PLMs) on one or multiple targeted tasks, especially under
resource-constrained use cases, such as edge devices. However, existing methods often struggle to balance domain-specific performance, retention of general
knowledge, and efficiency for training and inference. To address these challenges,
we propose Modular Domain Experts (MoDE). MoDE is a mixture-of-experts
architecture that augments a general PLMs with modular, domain-specialized
experts. These experts are trained independently and composed together via a
lightweight training process. In contrast to standard low-rank adaptation methods,
each MoDE expert consists of several transformer layers which scale better with
more training examples and larger parameter counts. Our evaluation demonstrates
that MoDE achieves comparable target performances to full parameter fine-tuning
while achieving 1.65% better retention performance. Moreover, MoDE’s architecture enables flexible sharding configurations and improves training speeds by
up to 38% over state-of-the-art distributed training configurations.
Primary Area: foundation or frontier models, including LLMs
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 12687
Loading