paper-with-me

홈 › Papers

Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency

2022-04-06 · ACL 2022 5 · Yanyang Li, Fuli Luo, Runxin Xu, Songfang Huang, Fei Huang, LiWei Wang

Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts. This work investigates three aspects of structured pruning on multilingual pre-trained language models: settings, algorithms, and efficiency. Experiments on nine downstream tasks show several counter-intuitive phenomena: for settings, individually pruning for each language does not induce a better result; for algorithms, the simplest method performs the best; for efficiency, a fast model does not imply that it is also small. To facilitate the comparison on all sparsity levels, we present Dynamic Sparsification, a simple approach that allows training the model once and adapting to different model sizes at inference. We hope this work fills the gap in the study of structured pruning on multilingual pre-trained models and sheds light on future research.

📄 PDF Abstract BibTeX arXiv:2204.02601

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing

2025-02-21 · Qi Le, Enmao Diao, Ziyan Wang, Xinran Wang 외

We introduce Probe Pruning (PP), a novel framework for online, dynamic, structured pruning of Large Language Models (LLMs) applied in a batch-wise manner. PP leverages the insight that not all samples and tokens contribu…

LINSPECTOR WEB: A Multilingual Probing Suite for Word Representations

2019-07-26 · IJCNLP 2019 11 · Max Eichler, Gözde Gül Şahin, Iryna Gurevych

We present LINSPECTOR WEB, an open source multilingual inspector to analyze word representations. Our system provides researchers working in low-resource settings with an easily accessible web based probing tool to gain …

Dependency Parsingnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2

Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers

2025-11-20 · Jian Ma, Qirong Peng, Xujie Zhu, Peixing Xie 외 arxiv

Diffusion Transformers (DiTs) have shown exceptional performance in image generation, yet their large parameter counts incur high computational costs, impeding deployment in resource-constrained settings. To address this…

Image Generation

DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization

2024-11-21 · Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Min Zhang 외

Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. Structured pruning reduces model size and speeds up inference but often causes uneven degra…

Language ModelingLanguage ModellingLarge Language Model

From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression

2021-12-14 · Runxin Xu, Fuli Luo, Chengyu Wang, Baobao Chang 외

Pre-trained Language Models (PLMs) have achieved great success in various Natural Language Processing (NLP) tasks under the pre-training and fine-tuning paradigm. With large quantities of parameters, PLMs are computation…

Contrastive LearningLanguage ModelingLanguage ModellingModel Compression+1