paper-with-me

Papers

Exploring Intrinsic Language-specific Subspaces in Fine-tuning Multilingual Neural Machine Translation

2024-09-08 · Zhe Cao, Zhi Qu, Hidetaka Kamigaito, Taro Watanabe

Multilingual neural machine translation models support fine-tuning hundreds of languages simultaneously. However, fine-tuning on full parameters solely is inefficient potentially leading to negative interactions among languages. In this work, we demonstrate that the fine-tuning for a language occurs in its intrinsic language-specific subspace with a tiny fraction of entire parameters. Thus, we propose language-specific LoRA to isolate intrinsic language-specific subspaces. Furthermore, we propose architecture learning techniques and introduce a gradual pruning schedule during fine-tuning to exhaustively explore the optimal setting and the minimal intrinsic subspaces for each language, resulting in a lightweight yet effective fine-tuning procedure. The experimental results on a 12-language subset and a 30-language subset of FLORES-101 show that our methods not only outperform full-parameter fine-tuning up to 2.25 spBLEU scores but also reduce trainable parameters to $0.4\%$ for high and medium-resource languages and $1.6\%$ for low-resource ones.

📄 PDF Abstract BibTeX arXiv:2409.05224

Code (1)

spike0924/lslo 공식 구현 pytorch

Tasks

Machine Translation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models

2023-05-27 · Zhong Zhang, Bang Liu, Junming Shao

Pre-trained language models (PLMs) are known to be overly parameterized and have significant redundancy, indicating a small degree of freedom of the PLMs. Motivated by the observation, in this paper, we study the problem…

Intrinsic Dimension Estimation via Nearest Constrained Subspace Classifier

2020-02-08 · Liang Liao, Stephen John Maybank

We consider the problems of classification and intrinsic dimension estimation on image data. A new subspace based classifier is proposed for supervised classification or intrinsic dimension estimation. The distribution o…

ClassificationGeneral Classification

Foundation Models for Semantic Novelty in Reinforcement Learning

2022-11-09 · Tarun Gupta, Peter Karkus, Tong Che, Danfei Xu 외

Effectively exploring the environment is a key challenge in reinforcement learning (RL). We address this challenge by defining a novel intrinsic reward based on a foundation model, such as contrastive language image pret…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Intrinsic Grassmann Averages for Online Linear, Robust and Nonlinear Subspace Learning

2017-02-03 · Rudrasis Chakraborty, Søren Hauberg, Baba C. Vemuri

Principal Component Analysis (PCA) and Kernel Principal Component Analysis (KPCA) are fundamental methods in machine learning for dimensionality reduction. The former is a technique for finding this approximation in fini…

Dimensionality Reduction

Intrinsic Subspace Evaluation of Word Embedding Representations

2016-06-25 · ACL 2016 8 · Yadollah Yaghoobzadeh, Hinrich Schütze

We introduce a new methodology for intrinsic evaluation of word representations. Specifically, we identify four fundamental criteria based on the characteristics of natural language that pose difficulties to NLP systems;…