AI Paper Atlas

Research map / Graph learning / GNN architectures

Auto Graph Encoder-Decoder for Neural Network Pruning

Sixing Yu, Arya Mazaheri, Ali Jannesari

ICCV 2021 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 46 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
use learned graph embedding instead of handcrafted 11-feature AMC embedding (ablation)RL pruning agent · CIFAR-10 ResNet-20, 50% FLOPserror rate (%): 10.2% -> 5.38%Improved
add stride-with-filters to stride-only handcrafted embedding (ablation)AMC embedding · CIFAR-10 ResNet-20, 50% FLOPserror rate (%): 31% -> 18%Improved
use all 11 handcrafted features instead of stride and filters (ablation)AMC embedding · CIFAR-10 ResNet-20, 50% FLOPserror rate (%): 18% -> 10.2%Improved
use learned graph embedding instead of no embedding (random search), 100 vs 300 episodes (ablation)RL pruning agent · CIFAR-10 ResNet-20validation accuracy (%): 88.41% -> 94.6%Improved
search with 100 episodes instead of 50 episodes (ablation)AGMC · CIFAR-10 ResNet-20validation accuracy (%): 93.8% -> 94.6%Improved
increase random search episodes from 200 to 300 (ablation)RS · CIFAR-10 ResNet-20validation accuracy (%): 71% -> 88.41%Improved
transfer encoder trained on ResNet-56 to ResNet-20 instead of training on ResNet-20 (ablation)AGMC · CIFAR-10 ResNet-20, 50% FLOPsvalidation accuracy (%): 94.6% -> 92.08%Hurt
use AGMC instead of RS at 90% FLOPs reduction (ablation)RL pruning agent · CIFAR-10 ResNet-56validation accuracy (%)Improved
use AGMC instead of RS at 10% FLOPs reduction (ablation)RL pruning agent · CIFAR-10 ResNet-56validation accuracy (%)No clear effect
use AGMC instead of AMCpruning policy · CIFAR-10 ResNet-56, 50% FLOPstest accuracy (%): 90.2 -> 92.76Improved
use AGMC instead of AMCpruning policy · CIFAR-10 ResNet-20, 50% FLOPstest accuracy (%): 86.4 -> 91.42Improved
use AGMC instead of AMCpruning policy · ImageNet MobileNet-v1, 40% FLOPstest accuracy (%): 68.90 -> 69.40Improved

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