https://github.com/leanderweber/layerwise-feedback-propagation
공식 코드Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation
Network Pruning That Matters: A Case Study on Retraining Variants
Dep-$L_0$: Improving $L_0$-based Network Sparsification via Dependency Modeling
Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters
A Simple and Effective Pruning Approach for Large Language Models
Comparing Rewinding and Fine-tuning in Neural Network Pruning
Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy
Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
An Information Theory-inspired Strategy for Automatic Network Pruning
Membership Inference Attacks and Defenses in Neural Network Pruning
Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning
Shapley Value as Principled Metric for Structured Network Pruning
Supervised Robustness-preserving Data-free Neural Network Pruning
FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning
EfficientTDNN: Efficient Architecture Search for Speaker Recognition
Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations
Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations
Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.