AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Exploring Lottery Ticket Hypothesis in Spiking Neural Networks

Youngeun Kim, Yuhang Li, Hyoungseob Park, Yeshwanth Venkatesha, Ruokai Yin, Priyadarshini Panda

ECCV 2022 · Architectures and efficiency › Pruning and efficient tuning · approach: Lottery ticket discovery · 45 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
add Early-Time search to IMP (ablation)IMP · CIFAR10 VGG16 (98.13% sparsity)accuracy and search speed: -0.71 acc, x1.35 speedMixed
add Early-Time search to IMP (ablation)IMP · CIFAR10 ResNet19 (98.13% sparsity)accuracy and search speed: -1.07 acc, x1.58 speedMixed
add Early-Time search to IMP (ablation)IMP · CIFAR100 ResNet19 (98.13% sparsity)accuracy and search speed: -1.86 acc, x1.57 speedMixed
add Early-Time search to IMP (ablation)IMP · CIFAR100 VGG16 (98.13% sparsity)accuracy and search speed: -1.61 acc, x1.36 speedMixed
add Early-Time search to Early-Bird ticket (ablation)EB ticket · CIFAR10 VGG16 (98.13% sparsity)accuracy and search speed: +0.22 acc, x1.12 speedMixed
add Early-Time search to Early-Bird ticket (ablation)EB ticket · CIFAR100 ResNet19 (98.13% sparsity)accuracy and search speed: -1.42 acc, x1.16 speedMixed
use Early-Bird ticket instead of IMPIMP · CIFAR10 VGG16 (98.13% sparsity)accuracy (%): 91.81 -> 84.64Hurt
use global instead of local pruning (ablation)IMP · CIFAR10 VGG16accuracy (%)Improved
use late rewinding in IMP (ablation)IMP · deep SNNsaccuracy (%)Improved
rewind to epoch 260 instead of early epoch (ablation)IMP · CIFAR10 VGG16 (98.13% sparsity)accuracy (%): ~1.5% drop at epoch 260Hurt
transfer ANN winning ticket to SNNIMP ticket from ANN · SVHN and Fashion-MNIST (98.13% sparsity)accuracy (%): less than 2% drop at 98.13% sparsityImproved
transfer ANN winning ticket to SNNIMP ticket from ANN · CIFAR10 and CIFAR100accuracy (%)Hurt

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