paper-with-me

홈 › Papers

LayerNorm: A key component in parameter-efficient fine-tuning

2024-03-29 · Taha ValizadehAslani, Hualou Liang

Fine-tuning a pre-trained model, such as Bidirectional Encoder Representations from Transformers (BERT), has been proven to be an effective method for solving many natural language processing (NLP) tasks. However, due to the large number of parameters in many state-of-the-art NLP models, including BERT, the process of fine-tuning is computationally expensive. One attractive solution to this issue is parameter-efficient fine-tuning, which involves modifying only a minimal segment of the model while keeping the remainder unchanged. Yet, it remains unclear which segment of the BERT model is crucial for fine-tuning. In this paper, we first analyze different components in the BERT model to pinpoint which one undergoes the most significant changes after fine-tuning. We find that output LayerNorm changes more than any other components when fine-tuned for different General Language Understanding Evaluation (GLUE) tasks. Then we show that only fine-tuning the LayerNorm can reach comparable, or in some cases better, performance to full fine-tuning and other parameter-efficient fine-tuning methods. Moreover, we use Fisher information to determine the most critical subset of LayerNorm and demonstrate that many NLP tasks in the GLUE benchmark can be solved by fine-tuning only a small portion of LayerNorm with negligible performance degradation.

📄 PDF Abstract BibTeX arXiv:2403.20284

Code (0)

등록된 구현이 없습니다.

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
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
WordPiece 설명 없음
Multi-Head Attention 설명 없음
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Pre-trained Models

2024-04-25 · Jiawei Chen, Dingkang Yang, Yue Jiang, Mingcheng Li 외

In the realm of Medical Visual Language Models (Med-VLMs), the quest for universal efficient fine-tuning mechanisms remains paramount, especially given researchers in interdisciplinary fields are often extremely short of…

Medical Visual Question Answeringparameter-efficient fine-tuningQuestion AnsweringVisual Question Answering

Exploiting Layer Normalization Fine-tuning in Visual Transformer Foundation Models for Classification

2025-08-11 · Zhaorui Tan, Tan Pan, Kaizhu Huang, Weimiao Yu 외 arxiv

LayerNorm is pivotal in Vision Transformers (ViTs), yet its fine-tuning dynamics under data scarcity and domain shifts remain underexplored. This paper shows that shifts in LayerNorm parameters after fine-tuning (LayerNo…

Transfer Learning

Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning

2023-12-18 · Bingchen Zhao, Haoqin Tu, Chen Wei, Jieru Mei 외

This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a domain adaptation process, i.e., transitio…

Domain AdaptationGPU

Parameter-Efficient Tuning on Layer Normalization for Pre-trained Language Models

2022-11-16 · Wang Qi, Yu-Ping Ruan, Yuan Zuo, Taihao Li

Conventional fine-tuning encounters increasing difficulties given the size of current Pre-trained Language Models, which makes parameter-efficient tuning become the focal point of frontier research. Previous methods in t…

Geometric Interpretation of Layer Normalization and a Comparative Analysis with RMSNorm

2024-09-19 · Akshat Gupta, Atahan Ozdemir, Gopala Anumanchipalli

This paper presents a novel geometric interpretation of LayerNorm and explores how LayerNorm influences the norm and orientation of hidden vectors in the representation space. With these geometric insights, we prepare th…