AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Autoencoder-based Graph Construction for Semi-supervised Learning

Mingeun Kang, Kiwon Lee, Yong H. Lee, Changho Suh

ECCV 2020 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 11 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 autoencoder-based graph to feature matching (ablation)supervised + feature matching · CIFAR-10 4000 labelserror rate (%): 13.99 -> 13.37Improved
add feature matching loss with autoencoder graph (ablation)Pi-model · CIFAR-10 4000 labelserror rate (%): 12.36 -> 10.81Improved
use autoencoder graph instead of plain graph (ablation)Pi-model + feature matching · CIFAR-10 4000 labelserror rate (%): 11.00 -> 10.81Improved
add feature matching loss with autoencoder graph (ablation)Mean Teacher · CIFAR-10 4000 labelserror rate (%): 12.31 -> 11.54Improved
use autoencoder graph instead of plain graph (ablation)Mean Teacher + feature matching · CIFAR-10 4000 labelserror rate (%): 12.12 -> 11.54Improved
add feature matching loss with autoencoder graph (ablation)ICT · CIFAR-10 4000 labelserror rate (%): 7.25 -> 6.87Improved
use autoencoder graph instead of plain graph (ablation)ICT + feature matching · CIFAR-10 4000 labelserror rate (%): 7.18 -> 6.87Improved
add consistency loss to supervised loss (ablation)supervised only · CIFAR-10 4000 labelserror rate (%): 20.26 -> 12.36Improved
add feature matching alone to supervised loss (ablation)supervised only · CIFAR-10 4000 labelserror rate (%): 20.26 -> 13.99Improved
replace alternating nuclear-norm matrix completion with jointly trained autoencodergraph-based SSL (GSCNN) · MNIST 100 labels, no augmentationerror rate (%): 62,240.97 s -> 20,108.16 s; 0.60 -> 0.57Improved
use fewer labels (relative gain over best baseline grows)Our model · MNISTerror rate (%): 13.6% at 100 labels, 31.9% at 50, 37.6% at 20Improved
use Wide ResNet-28 instead of CNN-13 with the methodOur model · CIFAR-10 4000 labelserror rate (%): 6.87 -> 6.24Improved

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