Saved in:
Bibliographic Details
Main Authors: Zou, Heming, Zang, Yunliang, Xu, Wutong, Zhu, Yao, Ji, Xiangyang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.08396
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912666272923648
author Zou, Heming
Zang, Yunliang
Xu, Wutong
Zhu, Yao
Ji, Xiangyang
author_facet Zou, Heming
Zang, Yunliang
Xu, Wutong
Zhu, Yao
Ji, Xiangyang
contents Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for foundation models, but it suffers from parameter interference, resulting in suboptimal performance. Although Mixture-of-Experts (MoE)-based LoRA variants show promise in mitigating intra-task correlations in single-task instruction tuning, they introduce additional router parameters and remain ineffective in multi-task model merging where inter-task interference arises. Inspired by the fly olfactory circuit, we propose FlyLoRA, an implicit MoE-based LoRA variant that introduces: (1) rank-wise expert activation in the up-projection matrix, and (2) an implicit router that unifies expert routing and down-projection, where a frozen sparse random projection matrix replaces the traditional dense trainable version. This design resolves the trade-off between intra-task decorrelation and computational efficiency by eliminating the need for an explicit router, while inherently mitigating inter-task interference due to the orthogonality property of random matrices. Extensive experiments across four domains -- general knowledge understanding, scientific question answering, mathematical reasoning, and code generation -- demonstrate consistent performance improvements over existing methods. Beyond empirical gains, FlyLoRA highlights how biological structures can inspire innovations in AI technologies. Code is available at https://github.com/gfyddha/FlyLoRA.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08396
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
Zou, Heming
Zang, Yunliang
Xu, Wutong
Zhu, Yao
Ji, Xiangyang
Machine Learning
Artificial Intelligence
Computation and Language
Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for foundation models, but it suffers from parameter interference, resulting in suboptimal performance. Although Mixture-of-Experts (MoE)-based LoRA variants show promise in mitigating intra-task correlations in single-task instruction tuning, they introduce additional router parameters and remain ineffective in multi-task model merging where inter-task interference arises. Inspired by the fly olfactory circuit, we propose FlyLoRA, an implicit MoE-based LoRA variant that introduces: (1) rank-wise expert activation in the up-projection matrix, and (2) an implicit router that unifies expert routing and down-projection, where a frozen sparse random projection matrix replaces the traditional dense trainable version. This design resolves the trade-off between intra-task decorrelation and computational efficiency by eliminating the need for an explicit router, while inherently mitigating inter-task interference due to the orthogonality property of random matrices. Extensive experiments across four domains -- general knowledge understanding, scientific question answering, mathematical reasoning, and code generation -- demonstrate consistent performance improvements over existing methods. Beyond empirical gains, FlyLoRA highlights how biological structures can inspire innovations in AI technologies. Code is available at https://github.com/gfyddha/FlyLoRA.
title FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2510.08396