paper-with-me

Papers

Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression

2021-05-05 · ICLR 2022 4 · Baeseong Park, Se Jung Kwon, Daehwan Oh, Byeongwook Kim, Dongsoo Lee

Even though fine-grained pruning techniques achieve a high compression ratio, conventional sparsity representations (such as CSR) associated with irregular sparsity degrade parallelism significantly. Practical pruning methods, thus, usually lower pruning rates (by structured pruning) to improve parallelism. In this paper, we study fixed-to-fixed (lossless) encoding architecture/algorithm to support fine-grained pruning methods such that sparse neural networks can be stored in a highly regular structure. We first estimate the maximum compression ratio of encoding-based compression using entropy. Then, as an effort to push the compression ratio to the theoretical maximum (by entropy), we propose a sequential fixed-to-fixed encoding scheme. We demonstrate that our proposed compression scheme achieves almost the maximum compression ratio for the Transformer and ResNet-50 pruned by various fine-grained pruning methods.

📄 PDF Abstract BibTeX arXiv:2105.01869

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compression

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Pruning 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces

2026-05-31 · Nasib Ullah, Jinbin Zhang, Jean Lucien Randrianantenaina, Erik Schultheis 외 arxiv

Extreme multi-label classification (XMC) involves learning models over large output spaces with millions of labels, making the output layer a memory-compute bottleneck. While sparsity-based methods reduce arithmetic comp…

Multi-Label Classification

LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts

2020-03-18 · Xinhai Liu, Zhizhong Han, Fangzhou Hong, Yu-Shen Liu 외

Learning discriminative feature directly on point clouds is still challenging in the understanding of 3D shapes. Recent methods usually partition point clouds into local region sets, and then extract the local region fea…

TETRIS: TilE-matching the TRemendous Irregular Sparsity

2018-12-01 · NeurIPS 2018 12 · Yu Ji, Ling Liang, Lei Deng, Youyang Zhang 외

Compressing neural networks by pruning weights with small magnitudes can significantly reduce the computation and storage cost. Although pruning makes the model smaller, it is difficult to get practical speedup in modern…

CPUGPU

A Weight Adaptation Trigger Mechanism in Decomposition-based Evolutionary Multi-Objective Optimisation

2025-02-23 · Xiaofeng Han, Xiaochen Chu, Tao Chao, Ming Yang 외

Decomposition-based multi-objective evolutionary algorithms (MOEAs) are widely used for solving multi-objective optimisation problems. However, their effectiveness depends on the consistency between the problems Pareto f…

Evolutionary Algorithms

Automated Tuning for Diffusion Inverse Problem Solvers without Generative Prior Retraining

2025-09-11 · Yaşar Utku Alçalar, Junno Yun, Mehmet Akçakaya arxiv

Diffusion/score-based models have recently emerged as powerful generative priors for solving inverse problems, including accelerated MRI reconstruction. While their flexibility allows decoupling the measurement model fro…

MRI Reconstruction