Papers with Code 아카이브
Network Pruning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 5
- 보존된 평가 기록
- 34
Network Pruning is a popular approach to reduce a heavy network to obtain a light-weight form by removing redundancy in the heavy network. In this approach, a complex over-parameterized network is first trained, then pruned based on come criterions, and finally fine-tuned to achieve comparable performance with reduced parameters.
Source: Ensemble Knowledge Distillation for Learning Improved and Efficient Networks
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning
Pruning neural network models for gene regulatory dynamics using data and domain knowledge
Structurally Prune Anything: Any Architecture, Any Framework, Any Time
SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
What to Do When Your Discrete Optimization Is the Size of a Neural Network?
Discriminative Adversarial Unlearning
Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models
EPSD: Early Pruning with Self-Distillation for Efficient Model Compression
Enhancing Scalability in Recommender Systems through Lottery Ticket Hypothesis and Knowledge Distillation-based Neural Network Pruning
GD doesn't make the cut: Three ways that non-differentiability affects neural network training
Block Pruning for Enhanced Efficiency in Convolutional Neural Networks
Fluctuation-based Adaptive Structured Pruning for Large Language Models
Picking the Underused Heads: A Network Pruning Perspective of Attention Head Selection for Fusing Dialogue Coreference Information
Neural Architecture Codesign for Fast Bragg Peak Analysis
Accelerating Convolutional Neural Network Pruning via Spatial Aura Entropy
An End-to-End Network Pruning Pipeline with Sparsity Enforcement
Towards Higher Ranks via Adversarial Weight Pruning
Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning
Neural Network Pruning by Gradient Descent
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
Data Augmentations in Deep Weight Spaces
Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks
Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models
Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks
Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning
Importance Estimation with Random Gradient for Neural Network Pruning
SparseByteNN: A Novel Mobile Inference Acceleration Framework Based on Fine-Grained Group Sparsity
Linear Mode Connectivity in Sparse Neural Networks
GraFT: Gradual Fusion Transformer for Multimodal Re-Identification
Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks
Filter Pruning For CNN With Enhanced Linear Representation Redundancy
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.