paper-with-me

홈 › Papers

Pruning Pre-trained Language Models with Principled Importance and Self-regularization

2023-05-21 · Siyu Ren, Kenny Q. Zhu

Iterative pruning is one of the most effective compression methods for pre-trained language models. We discovered that finding the optimal pruning decision is an equality-constrained 0-1 Integer Linear Programming problem. The solution to this optimization problem leads to a principled importance criterion which we use to rank parameters during iterative model pruning. To mitigate the poor generalization at high sparsity levels, we propose a self-regularization scheme where model prediction is regularized by the latest checkpoint with increasing sparsity throughout pruning. Our experiments on natural language understanding, question-answering, named entity recognition, and data-to-text generation with various Transformer-based PLMs show the effectiveness of the approach at various sparsity levels.

📄 PDF Abstract BibTeX arXiv:2305.12394

Code (1)

drsy/pins 공식 구현 pytorch

Tasks

Data-to-Text Generationnamed-entity-recognitionNamed Entity RecognitionNatural Language UnderstandingQuestion AnsweringText Generation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Entropy Reveals Block Importance in Masked Self-Supervised Vision Transformers

2026-02-03 · Peihao Xiang, Kaida Wu, Ou Bai arxiv

Masked self-supervised vision transformers have become a dominant pretraining paradigm, yet their substantial model size poses significant challenges for resource-constrained deployment and efficient transfer learning. A…

Transfer LearningModel Compression

AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models

2024-10-14 · Haiquan Lu, Yefan Zhou, Shiwei Liu, Zhangyang Wang 외

Recent work on pruning large language models (LLMs) has shown that one can eliminate a large number of parameters without compromising performance, making pruning a promising strategy to reduce LLM model size. Existing L…

Max-Affine Spline Insights Into Deep Network Pruning

2021-01-07 · Haoran You, Randall Balestriero, Zhihan Lu, Yutong Kou 외

In this paper, we study the importance of pruning in Deep Networks (DNs) and the yin & yang relationship between (1) pruning highly overparametrized DNs that have been trained from random initialization and (2) training …

Network Pruning

Exploring Weight Importance and Hessian Bias in Model Pruning

2020-06-19 · Mingchen Li, Yahya Sattar, Christos Thrampoulidis, Samet Oymak

Model pruning is an essential procedure for building compact and computationally-efficient machine learning models. A key feature of a good pruning algorithm is that it accurately quantifies the relative importance of th…

Pruning as a Game: Equilibrium-Driven Sparsification of Neural Networks

2025-12-26 · Zubair Shah, Noaman Khan arxiv

Neural network pruning is widely used to reduce model size and computational cost. Yet, most existing methods treat sparsity as an externally imposed constraint, enforced through heuristic importance scores or training-t…

Network Pruning