paper-with-me

홈 › Papers

Asymmetry in Low-Rank Adapters of Foundation Models

2024-02-26 · Jiacheng Zhu, Kristjan Greenewald, Kimia Nadjahi, Haitz Sáez de Ocáriz Borde, Rickard Brüel Gabrielsson, Leshem Choshen, Marzyeh Ghassemi, Mikhail Yurochkin, Justin Solomon

Parameter-efficient fine-tuning optimizes large, pre-trained foundation models by updating a subset of parameters; in this class, Low-Rank Adaptation (LoRA) is particularly effective. Inspired by an effort to investigate the different roles of LoRA matrices during fine-tuning, this paper characterizes and leverages unexpected asymmetry in the importance of low-rank adapter matrices. Specifically, when updating the parameter matrices of a neural network by adding a product $BA$, we observe that the $B$ and $A$ matrices have distinct functions: $A$ extracts features from the input, while $B$ uses these features to create the desired output. Based on this observation, we demonstrate that fine-tuning $B$ is inherently more effective than fine-tuning $A$, and that a random untrained $A$ should perform nearly as well as a fine-tuned one. Using an information-theoretic lens, we also bound the generalization of low-rank adapters, showing that the parameter savings of exclusively training $B$ improves the bound. We support our conclusions with experiments on RoBERTa, BART-Large, LLaMA-2, and ViTs.

📄 PDF Abstract BibTeX arXiv:2402.16842

Code (1)

Jiacheng-Zhu-AIML/AsymmetryLoRA 공식 구현 pytorch

Tasks

parameter-efficient fine-tuning

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
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 $x$…
WordPiece 설명 없음
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
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

Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters

2025-06-17 · Anastasis Kratsios, Tin Sum Cheng, Aurelien Lucchi, Haitz Sáez de Ocáriz Borde

Low-Rank Adaptation (LoRA) has emerged as a widely adopted parameter-efficient fine-tuning (PEFT) technique for foundation models. Recent work has highlighted an inherent asymmetry in the initialization of LoRA's low-ran…

Generalization Boundsparameter-efficient fine-tuning

LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters

2026-05-13 · Beomjin Ahn, Jungmin Kwon, Chanyong Jung, Jaewook Chung arxiv

Foundation models and low-rank adapters enable efficient on-device generative AI but raise risks such as intellectual property leakage and model recovery attacks. Existing defenses are often impractical because they requ…

Efficient and Scalable Fine-Tune of Language Models for Genome Understanding

2024-02-12 · Huixin Zhan, Ying Nian Wu, Zijun Zhang

Although DNA foundation models have advanced the understanding of genomes, they still face significant challenges in the limited scale and diversity of genomic data. This limitation starkly contrasts with the success of …

Genome Understanding

A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models

2025-02-20 · Mengyang Sun, Yihao Wang, Tao Feng, Dan Zhang 외

In order to streamline the fine-tuning of foundation models, Low-Rank Adapters (LoRAs) have been substantially adopted across various fields, including instruction tuning and domain adaptation. The underlying concept of …

Domain Adaptation

Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation

2024-05-24 · Abhinav Jain, Swarat Chaudhuri, Thomas Reps, Chris Jermaine

Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require storing multiple task-specific adapters, cre…

Code GenerationNatural Language Understandingparameter-efficient fine-tuning