AI Paper Atlas

Research map / Graph learning / GNN architectures

Understanding the Dynamics of DNNs Using Graph Modularity

Yao Lu, Wen Yang, Yunzhe Zhang, Zuohui Chen, Jinyin Chen, Qi Xuan, Zhen Wang, Xiaoniu Yang

ECCV 2022 · Graph learning › GNN architectures · approach: GNN generalization theory · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
remove the plateau layers (last Conv-BN-ReLU layers) from VGG19 one by one (ablation)VGG19 · CIFAR-10accuracyNo clear effect
remove stage-3 bottleneck blocks of ResNet152 where modularity plateaus (ablation)ResNet152 · CIFAR-10 and ImageNet50accuracyNo clear effect
prune a VGG11 layer with small modularity increase (0.01) vs large (0.16) (ablation)VGG11 · CIFAR-10accuracy drop: 0.01% vs 0.57% degradationHurt
prune a VGG11 layer with modularity increase 0.08 vs 0.26 (ablation)VGG11 · CIFAR-100accuracy drop: 0.37% vs 2.11%Hurt
modularity-guided layer pruning of ResNet56 vs Chen et alResNet56 · CIFAR-10FLOPs reduction: 34.80% -> 60.30%Improved
modularity-guided layer pruning of ResNet56 vs Chen et alResNet56 · CIFAR-10top-1 accuracy (%): 93.29 -> 93.38Improved
modularity-guided layer pruning of ResNet56 vs DBP-0.5ResNet56 · CIFAR-10FLOPs reduction: 53.41% -> 60.30%Improved
vary batch size N (200 to 5000) when building graphs (ablation)modularity curve · CIFAR-10 (VGG16, ResNet18)modularity curveNo clear effect
vary k from 3 to 11 in k-NN graph (ablation)modularity curve · CIFAR-10modularity curveNo clear effect
increase k to 100-400 in k-NN graph (ablation)modularity curve · CIFAR-10modularity valueHurt
replace cosine similarity with Pearson correlation for the similarity matrix (ablation)modularity curve · CIFAR-10modularity curveNo clear effect
use randomly initialized models instead of trained models (ablation)modularity curve · CIFAR-10 (VGG16, ResNet18)modularity trendHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy