paper-with-me

Papers

Inf-CP: A Reliable Channel Pruning based on Channel Influence

2021-12-05 · Bilan Lai, Haoran Xiang, Furao Shen

One of the most effective methods of channel pruning is to trim on the basis of the importance of each neuron. However, measuring the importance of each neuron is an NP-hard problem. Previous works have proposed to trim by considering the statistics of a single layer or a plurality of successive layers of neurons. These works cannot eliminate the influence of different data on the model in the reconstruction error, and currently, there is no work to prove that the absolute values of the parameters can be directly used as the basis for judging the importance of the weights. A more reasonable approach is to eliminate the difference between batch data that accurately measures the weight of influence. In this paper, we propose to use ensemble learning to train a model for different batches of data and use the influence function (a classic technique from robust statistics) to learn the algorithm to track the model's prediction and return its training parameter gradient, so that we can determine the responsibility for each parameter, which we call "influence", in the prediction process. In addition, we theoretically prove that the back-propagation of the deep network is a first-order Taylor approximation of the influence function of the weights. We perform extensive experiments to prove that pruning based on the influence function using the idea of ensemble learning will be much more effective than just focusing on error reconstruction. Experiments on CIFAR shows that the influence pruning achieves the state-of-the-art result.

📄 PDF Abstract BibTeX arXiv:2112.02521

Code (0)

등록된 구현이 없습니다.

Tasks

Ensemble Learning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining

2023-08-13 · Hongrong Cheng, Miao Zhang, Javen Qinfeng Shi

A challenge of channel pruning is designing efficient and effective criteria to select channels to prune. A widely used criterion is minimal performance degeneration. To accurately evaluate the truth performance degenera…

Channel Pruning Guided by Classification Loss and Feature Importance

2020-03-15 · Jinyang Guo, Wanli Ouyang, Dong Xu

In this work, we propose a new layer-by-layer channel pruning method called Channel Pruning guided by classification Loss and feature Importance (CPLI). In contrast to the existing layer-by-layer channel pruning approach…

ClassificationFeature ImportanceGeneral Classification

Carrying out CNN Channel Pruning in a White Box

2021-04-24 · Yuxin Zhang, Mingbao Lin, Chia-Wen Lin, Jie Chen 외

Channel Pruning has been long studied to compress CNNs, which significantly reduces the overall computation. Prior works implement channel pruning in an unexplainable manner, which tends to reduce the final classificatio…

image-classificationImage Classification

Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks

2026-05-20 · Qishi Zhan, Ziheng Chen, Minxuan Hu arxiv

One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime, even when the pruning mask preserves the largest weights. We argue that this failure reflects a granularity mismatch in post-prun…

Channel-wise Influence: Estimating Data Influence for Multivariate Time Series

2024-08-27 · Muyao Wang, Zeke Xie, Bo Chen

The influence function, a technique from robust statistics, measures the impact on model parameters or related functions when training data is removed or modified. This effective and valuable post-hoc method allows for s…

Anomaly DetectionTime Series