paper-with-me

Papers

ROSA: Random Subspace Adaptation for Efficient Fine-Tuning

2024-07-10 · Marawan Gamal Abdel Hameed, Aristides Milios, Siva Reddy, Guillaume Rabusseau

Model training requires significantly more memory, compared with inference. Parameter efficient fine-tuning (PEFT) methods provide a means of adapting large models to downstream tasks using less memory. However, existing methods such as adapters, prompt tuning or low-rank adaptation (LoRA) either introduce latency overhead at inference time or achieve subpar downstream performance compared with full fine-tuning. In this work we propose Random Subspace Adaptation (ROSA), a method that outperforms previous PEFT methods by a significant margin, while maintaining a zero latency overhead during inference time. In contrast to previous methods, ROSA is able to adapt subspaces of arbitrarily large dimension, better approximating full-finetuning. We demonstrate both theoretically and experimentally that this makes ROSA strictly more expressive than LoRA, without consuming additional memory during runtime. As PEFT methods are especially useful in the natural language processing domain, where models operate on scales that make full fine-tuning very expensive, we evaluate ROSA in two common NLP scenarios: natural language generation (NLG) and natural language understanding (NLU) with GPT-2 and RoBERTa, respectively. We show that on almost every GLUE task ROSA outperforms LoRA by a significant margin, while also outperforming LoRA on NLG tasks. Our code is available at https://github.com/rosa-paper/rosa

📄 PDF Abstract BibTeX arXiv:2407.07802

Code (1)

rosa-paper/rosa 공식 구현 pytorch

Tasks

Natural Language Understandingparameter-efficient fine-tuningText Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Multi-Head Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models

2025-11-21 · Dayan Pan, Jingyuan Wang, Yilong Zhou, Jiawei Cheng 외 arxiv

Fine-tuning large language models is essential for task-specific adaptation, yet it remains computationally prohibitive. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a solution, but current approaches t…

parameter-efficient fine-tuning

RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation

2024-01-09 · Mahdi Nikdan, Soroush Tabesh, Elvir Crnčević, Dan Alistarh

We investigate parameter-efficient fine-tuning (PEFT) methods that can provide good accuracy under limited computational and memory budgets in the context of large language models (LLMs). We present a new PEFT method cal…

GPUMathparameter-efficient fine-tuningQuantization

MiCA Learns More Knowledge Than LoRA and Full Fine-Tuning

2026-04-02 · Sten Rüdiger, Sebastian Raschka arxiv

Minor Component Adaptation (MiCA) is a novel parameter-efficient fine-tuning method for large language models that focuses on adapting underutilized subspaces of model representations. Unlike conventional methods such as…

parameter-efficient fine-tuning

LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection

2026-05-12 · Lanxin Zhao, Bamdev Mishra, Pratik Jawanpuria, Lequan Lin 외 arxiv

Orthogonal parameter-efficient fine-tuning (PEFT) adapts pretrained weights through structure-preserving multiplicative transformations, but existing methods often conflate two distinct design choices: the subspace in wh…

parameter-efficient fine-tuningMathematical Reasoning

Complementary Subspace Low-Rank Adaptation of Vision-Language Models for Few-Shot Classification

2025-01-25 · Zhongqi Wang, Jia Dai, Kai Li, Xu Li 외

Vision language model (VLM) has been designed for large scale image-text alignment as a pretrained foundation model. For downstream few shot classification tasks, parameter efficient fine-tuning (PEFT) VLM has gained muc…

Few-Shot Learningparameter-efficient fine-tuning