3 citations · 5 across the 18 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
cs.LG2021
RGP: Neural Network Pruning through Its Regular Graph Structure
Zhuangzhi Chen, Jingyang Xiang, Yao Lu +2
Lightweight model design has become an important direction in the application of deep learning technology, pruning is an effective mean to achieve a large reduction in model parame…
cs.CV2021
Understanding the Dynamics of DNNs Using Graph Modularity
Yao Lu, Wen Yang, Yunzhe Zhang +5
There are good arguments to support the claim that deep neural networks (DNNs) capture better feature representations than the previous hand-crafted feature engineering, which lead…
cs.LG2021★ 3 cited
Graph-Based Similarity of Neural Network Representations
Zuohui Chen, Yao Lu, Jinxuan Hu +4
Understanding the black-box representations in Deep Neural Networks (DNN) is an essential problem in deep learning. In this work, we propose Graph-Based Similarity (GBS) to measure…