paper-with-me

홈 › Papers

Adaptive Pruning of Pretrained Transformer via Differential Inclusions

2025-01-06 · Yizhuo Ding, Ke Fan, Yikai Wang, Xinwei Sun, Yanwei Fu

Large transformers have demonstrated remarkable success, making it necessary to compress these models to reduce inference costs while preserving their perfor-mance. Current compression algorithms prune transformers at fixed compression ratios, requiring a unique pruning process for each ratio, which results in high computational costs. In contrast, we propose pruning of pretrained transformers at any desired ratio within a single pruning stage, based on a differential inclusion for a mask parameter. This dynamic can generate the whole regularization solution path of the mask parameter, whose support set identifies the network structure. Therefore, the solution path identifies a Transformer weight family with various sparsity levels, offering greater flexibility and customization. In this paper, we introduce such an effective pruning method, termed SPP (Solution Path Pruning). To achieve effective pruning, we segment the transformers into paired modules, including query-key pairs, value-projection pairs, and sequential linear layers, and apply low-rank compression to these pairs, maintaining the output structure while enabling structural compression within the inner states. Extensive experiments conducted on various well-known transformer backbones have demonstrated the efficacy of SPP.

📄 PDF Abstract BibTeX arXiv:2501.03289

Code (0)

등록된 구현이 없습니다.

Tasks

Low-rank compression

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Residual Connection 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…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Set-Valued Risk Measures as Backward Stochastic Difference Inclusions and Equations

2019-12-14 · Çağın Ararat, Zachary Feinstein

Scalar dynamic risk measures for univariate positions in continuous time are commonly represented as backward stochastic differential equations. In the multivariate setting, dynamic risk measures have been defined and st…

Split LBI for Deep Learning: Structural Sparsity via Differential Inclusion Paths

2019-09-25 · Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun 외

Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error. However, compressive networks are desired in…

A fast algorithm for solving the lasso problem exactly without homotopy using differential inclusions

2025-07-08 · Gabriel P. Langlois, Jérôme Darbon arxiv

We prove in this work that the well-known lasso problem can be solved exactly without homotopy using novel differential inclusions techniques. Specifically, we show that a selection principle from the theory of different…

Finite-Time Convergence of Continuous-Time Optimization Algorithms via Differential Inclusions

2019-12-18 · Orlando Romero, Mouhacine Benosman

In this paper, we propose two discontinuous dynamical systems in continuous time with guaranteed prescribed finite-time local convergence to strict local minima of a given cost function. Our approach consists of exploiti…

Movement Pruning: Adaptive Sparsity by Fine-Tuning

2020-05-15 · NeurIPS 2020 12 · Victor Sanh, Thomas Wolf, Alexander M. Rush

Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; however, it is less effective in the transfer learning regime that has become standard for state-of-the-art natural languag…

Network PruningTransfer Learning