https://github.com/thu-keg/skill-neuron
공식 코드Finding Skill Neurons in Pre-trained Transformer-based Language Models
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
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/transmuteai/light-weight-trackers
공식 코드On Designing Light-Weight Object Trackers through Network Pruning: Use CNNs or Transformers?
https://github.com/uni-tubingen-teamproject/network-pruning-and-interpretability
공식 코드Investigating the Effect of Network Pruning on Performance and Interpretability
https://github.com/vanderschuea/stthree
공식 코드Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?
https://github.com/vidhur2k/CS8803-Project
공식 코드Efficient Incorporation of Multiple Latency Targets in the Once-For-All Network
https://github.com/vila-lab/gblm-pruner
공식 코드Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models
https://github.com/vita-group/backdoor-lth
공식 코드Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free
https://github.com/vita-group/certifiedpruning
공식 코드Can pruning improve certified robustness of neural networks?
https://github.com/wustl-cig/mbdl_pruning
공식 코드Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning
https://github.com/wyxscir/cfsp
공식 코드CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information
https://github.com/x-zho14/ProbMask-official
공식 코드Effective Sparsification of Neural Networks with Global Sparsity Constraint
https://github.com/xidongwu/autotrainonce
공식 코드Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch
https://github.com/xingyul/Sparse-Winograd-CNN
공식 코드https://github.com/xxlifelover/meta-gradient-augmentation
공식 코드Improving Generalization in Meta-Learning via Meta-Gradient Augmentation
https://github.com/yefanzhou/threeregimepruning
공식 코드https://github.com/yeshaokai/Robustness-Aware-Pruning-ADMM
공식 코드https://github.com/yitewang/ntk-sap
공식 코드NTK-SAP: Improving neural network pruning by aligning training dynamics
https://github.com/yochaiz/Slimmable
공식 코드Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks
https://github.com/yochaiz/darts-UNIQ
공식 코드Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks
https://github.com/yoniaflalo/knapsack_pruning
공식 코드https://github.com/youlei202/entropic-wasserstein-pruning
공식 코드SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning
https://github.com/yusx-swapp/gnn-rl-model-compression
공식 코드Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning
https://github.com/zib-iol/bimp
공식 코드https://github.com/zib-iol/compression-aware-sfw
공식 코드Compression-aware Training of Neural Networks using Frank-Wolfe
https://github.com/zycdev/cmploss
공식 코드Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding
https://github.com/zyxxmu/dsnot
공식 코드Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
https://github.com/zyxxmu/lottery-jackpots
공식 코드https://github.com/2023-MindSpore-1/ms-code-18/tree/main/ManiDP
https://github.com/2023-MindSpore-1/ms-code-217/tree/main/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/2023-MindSpore-4/Code-5/tree/main/ManiDP
https://github.com/2023-MindSpore-4/Code11/tree/main/squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/ARMargolis/melanoma-pytorch
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
https://github.com/Adamdad/Samesame
Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization
https://github.com/Adlik/model_optimizer
https://github.com/AlexandruBurlacu/keras_squeezenet
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
https://github.com/AlumLuther/PruningFilters
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.