paper-with-me

Papers

Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning

2025-10-01 · Minghao Yang, Ren Togo, Guang Li, Takahiro Ogawa, Miki Haseyama arxiv

Mixture-of-Experts (MoE) has emerged as a powerful framework for multi-task learning (MTL). However, existing MoE-MTL methods often rely on single-task pretrained backbones and suffer from redundant adaptation and inefficient knowledge sharing during the transition from single-task to multi-task learning (STL to MTL). To address these limitations, we propose adaptive shared experts (ASE) within a low-rank adaptation (LoRA) based MoE, where shared experts are assigned router-computed gating weights jointly normalized with sparse experts. This design facilitates STL to MTL transition, enhances expert specialization, and cooperation. Furthermore, we incorporate fine-grained experts by increasing the number of LoRA experts while proportionally reducing their rank, enabling more effective knowledge sharing under a comparable parameter budget. Extensive experiments on the PASCAL-Context benchmark, under unified training settings, demonstrate that ASE consistently improves performance across diverse configurations and validates the effectiveness of fine-grained designs for MTL.

📄 PDF Abstract BibTeX arXiv:2510.00570

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learning

Similar Papers 제목 키워드 기반

CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging

2026-02-28 · Jie Cao, Zhenxuan Fan, Zhuonan Wang, Tianwei Lin 외 arxiv

Large language models (LLMs) achieve remarkable performance on diverse downstream and domain-specific tasks via parameter-efficient fine-tuning (PEFT). However, existing PEFT methods, particularly MoE-LoRA architectures,…

parameter-efficient fine-tuning

AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts

2024-05-01 · Zefang Liu, Jiahua Luo

We introduce AdaMoLE, a novel method for fine-tuning large language models (LLMs) through an Adaptive Mixture of Low-Rank Adaptation (LoRA) Experts. Moving beyond conventional methods that employ a static top-k strategy …

Multiple Choice Question Answering (MCQA)

Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs

2026-06-30 · Seyed Alireza Molavi, Zhan Su, Yan Hu, Peyman Sheikholharam Mashhadi 외 arxiv

Composing independently trained LoRA adapters into a single large language model is useful for multi-domain adaptation, especially when the original training data cannot be shared. A common approach is to use MoE-style r…

Reinforcement LearningDomain Adaptation

Spend Experts Where You Are Unsure: Confidence-Adaptive Routing for Mixture-of-Experts LoRA

2026-07-28 · Tom Saliencro, Rohan Desai, Priya Nair, Maya Lindqvist 외 arxiv

Mixture-of-Experts (MoE) variants of Low-Rank Adaptation (LoRA) route every token to a fixed number of experts $k$. Tokens differ in how uncertain the model is about them, so a single k over-spends on easy tokens and und…

Out-of-Distribution Detection

SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning

2026-04-21 · Boyan Shi, Wei Chen, Shuyuan Zhao, Junfeng Shen 외 arxiv

The combination of Mixture-of-Experts (MoE) and Low-Rank Adaptation (LoRA) has shown significant potential for enhancing the multi-task learning capabilities of Large Language Models. However, existing methods face two p…

parameter-efficient fine-tuningMulti-Task Learning