paper-with-me

홈 › Papers

Comparative Analysis of Efficient Adapter-Based Fine-Tuning of State-of-the-Art Transformer Models

2025-01-14 · Saad Mashkoor Siddiqui, Mohammad Ali Sheikh, Muhammad Aleem, Kajol R Singh

In this work, we investigate the efficacy of various adapter architectures on supervised binary classification tasks from the SuperGLUE benchmark as well as a supervised multi-class news category classification task from Kaggle. Specifically, we compare classification performance and time complexity of three transformer models, namely DistilBERT, ELECTRA, and BART, using conventional fine-tuning as well as nine state-of-the-art (SoTA) adapter architectures. Our analysis reveals performance differences across adapter architectures, highlighting their ability to achieve comparable or better performance relative to fine-tuning at a fraction of the training time. Similar results are observed on the new classification task, further supporting our findings and demonstrating adapters as efficient and flexible alternatives to fine-tuning. This study provides valuable insights and guidelines for selecting and implementing adapters in diverse natural language processing (NLP) applications.

📄 PDF Abstract BibTeX arXiv:2501.08271

Code (0)

등록된 구현이 없습니다.

Tasks

Binary ClassificationClassification

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
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…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
BART BART is a denoising autoencoder for pretraining sequence-to-sequence models. It is trained by (1) corrupting text…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Enhancing AI Safety Through the Fusion of Low Rank Adapters

2024-12-30 · Satya Swaroop Gudipudi, Sreeram Vipparla, Harpreet Singh, Shashwat Goel 외

Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models generate harmful responses when faced with …

Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language Models

2026-05-27 · Prasanth K K arxiv

Low-Rank Adaptation (LoRA) has emerged as a widely adopted approach for adapting large language models, yet the internal representational changes induced by LoRA fine-tuning remain insufficiently understood. In this work…

A Comprehensive Analysis of Adapter Efficiency

2023-05-12 · Nandini Mundra, Sumanth Doddapaneni, Raj Dabre, Anoop Kunchukuttan 외

Adapters have been positioned as a parameter-efficient fine-tuning (PEFT) approach, whereby a minimal number of parameters are added to the model and fine-tuned. However, adapters have not been sufficiently analyzed to u…

Natural Language Understandingparameter-efficient fine-tuning

Lightweight Adapter Tuning for Multilingual Speech Translation

2021-06-02 · ACL 2021 5 · Hang Le, Juan Pino, Changhan Wang, Jiatao Gu 외

Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting lightweight modules between layers, resulting…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognition+3

AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection

2025-05-15 · Bin-Bin Gao, Yue Zhou, Jiangtao Yan, Yuezhi Cai 외

Universal visual anomaly detection aims to identify anomalies from novel or unseen vision domains without additional fine-tuning, which is critical in open scenarios. Recent studies have demonstrated that pre-trained vis…

Anomaly Detection