paper-with-me

홈 › Papers

Matrix-Transformation Based Low-Rank Adaptation (MTLoRA): A Brain-Inspired Method for Parameter-Efficient Fine-Tuning

2024-03-12 · Yao Liang, Yuwei Wang, Yang Li, Yi Zeng

Fine-tuning techniques based on Large Pretrained Language Models (LPLMs) have been proven to significantly enhance model performance on a variety of downstream tasks and effectively control the output behaviors of LPLMs. Recent studies have proposed numerous methods for fine-tuning a small number of parameters based on open-source LPLMs, reducing the demand for computational and storage resources. Among these, reparameterization fine-tuning methods represented by LoRA (Low-Rank Adaptation) have gained popularity. We find that although these methods perform well in many aspects, there is still considerable room for improvement in terms of complex task adaptability, performance, stability, and algorithm complexity. In response to this, inspired by the idea that the functions of the brain are shaped by its geometric structure, this paper integrates this idea into LoRA technology and proposes a new matrix transformation-based reparameterization method for efficient fine-tuning, named Matrix-Transformation based Low-Rank Adaptation (MTLoRA). MTLoRA aims to dynamically alter its spatial geometric structure by applying a transformation-matrix T to perform linear transformations, such as rotation, scaling, and translation, on the task-specific parameter matrix, generating new matrix feature patterns (eigenvectors) to mimic the fundamental influence of complex geometric structure feature patterns in the brain on functions, thereby enhancing the model's performance in downstream tasks. In Natural Language Understanding (NLU) tasks, it is evaluated using the GLUE benchmark test, and the results reveal that MTLoRA achieves an overall performance increase of about 1.0% across eight tasks; in Natural Language Generation (NLG) tasks, MTLoRA improves performance by an average of 0.95% and 0.56% in the DART and WebNLG tasks, respectively.

📄 PDF Abstract BibTeX arXiv:2403.07440

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Understandingparameter-efficient fine-tuningText Generation

Methods 이 논문이 사용한 방법론

DART # 🎯 DART-Math > Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving 📝 Paper@arXiv | 🤗…

Similar Papers 제목 키워드 기반

MTLoRA: Low-Rank Adaptation Approach for Efficient Multi-Task Learning

2024-01-01 · CVPR 2024 1 · Ahmed Agiza, Marina Neseem, Sherief Reda

Adapting models pre-trained on large-scale datasets to a variety of downstream tasks is a common strategy in deep learning. Consequently parameter-efficient fine-tuning methods have emerged as a promising way to adap…

Multi-Task Learningparameter-efficient fine-tuning

MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning

2024-03-29 · Ahmed Agiza, Marina Neseem, Sherief Reda

Adapting models pre-trained on large-scale datasets to a variety of downstream tasks is a common strategy in deep learning. Consequently, parameter-efficient fine-tuning methods have emerged as a promising way to adapt p…

Multi-Task Learningparameter-efficient fine-tuning

Scalable Multi-Task Low-Rank Model Adaptation

2026-03-02 · Zichen Tian, Antoine Ledent, Qianru Sun arxiv

Scaling multi-task low-rank adaptation (LoRA) to a large number of tasks induces catastrophic performance degradation, such as an accuracy drop from 88.2% to 2.0% on DOTA when scaling from 5 to 15 tasks. This failure is …

Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation

2024-10-30 · Wei Dong, Yuan Sun, Yiting Yang, Xing Zhang 외

A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed i…

parameter-efficient fine-tuning

LoRMA: Low-Rank Multiplicative Adaptation for LLMs

2025-06-09 · Harsh Bihany, Shubham Patel, Ashutosh Modi

Large Language Models have shown remarkable capabilities in the NLP domain. Their effectiveness can mainly be attributed to their ability to adapt to an array of downstream tasks. However, generally, full fine-tuning is …