paper-with-me

홈 › Papers

SiRA: Sparse Mixture of Low Rank Adaptation

2023-11-15 · Yun Zhu, Nevan Wichers, Chu-Cheng Lin, Xinyi Wang, Tianlong Chen, Lei Shu, Han Lu, Canoee Liu, Liangchen Luo, Jindong Chen, Lei Meng

Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks. Most previous works considers adding the dense trainable parameters, where all parameters are used to adapt certain task. We found this less effective empirically using the example of LoRA that introducing more trainable parameters does not help. Motivated by this we investigate the importance of leveraging "sparse" computation and propose SiRA: sparse mixture of low rank adaption. SiRA leverages the Sparse Mixture of Expert(SMoE) to boost the performance of LoRA. Specifically it enforces the top $k$ experts routing with a capacity limit restricting the maximum number of tokens each expert can process. We propose a novel and simple expert dropout on top of gating network to reduce the over-fitting issue. Through extensive experiments, we verify SiRA performs better than LoRA and other mixture of expert approaches across different single tasks and multitask settings.

📄 PDF Abstract BibTeX arXiv:2311.09179

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

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…

Similar Papers 제목 키워드 기반

MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning

2024-10-30 · Xujia Wang, Haiyan Zhao, Shuo Wang, Hanqing Wang 외

Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have significantly improved the adaptation of LLMs to downstream tasks in a resource-efficient manner. However, in multi-task scenarios, challenges such as trainin…

Computational EfficiencyMixture-of-ExpertsMulti-Task Learningparameter-efficient fine-tuning

Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution

2025-11-20 · Xiao He, Zhijun Tu, Kun Cheng, Mingrui Zhu 외 arxiv

The demonstrated success of sparsely-gated Mixture-of-Experts (MoE) architectures, exemplified by models such as DeepSeek and Grok, has motivated researchers to investigate their adaptation to diverse domains. In real-wo…

Image Super-Resolution

HELLoRA: Hot Experts Layer-Level Low-Rank Adaptation for Mixture-of-Experts Models

2026-05-11 · Jia Wei, Zhonghao Zhang, Ping Chen, Qianyang li 외 arxiv

Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning of large language models, yet most variants target dense architectures. Mixture-of-Experts (MoE) models scale parameters at near-constant per-token com…

parameter-efficient fine-tuningMathematical ReasoningCode Generation

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

2025-10-01 · Minghao Yang, Ren Togo, Guang Li, Takahiro Ogawa 외 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 ineffi…

Multi-Task Learning

L-MoE: End-to-End Training of a Lightweight Mixture of Low-Rank Adaptation Experts

2025-10-19 · Shihao Ji, Zihui Song arxiv

The Mixture of Experts (MoE) architecture enables the scaling of Large Language Models (LLMs) to trillions of parameters by activating a sparse subset of weights for each input, maintaining constant computational cost du…