AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Diffusion Mechanism in Residual Neural Network: Theory and Applications

Tangjun Wang, Zehao Dou, Chenglong Bao, Zuoqiang Shi

TPAMI 2023 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 30 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 diffusion layers to ResNet (ablation)ResNet · Cora node classificationaccuracy: 58.9 -> 82.1Improved
add diffusion layers to ResNet (ablation)ResNet · Citeseer node classificationaccuracy: 61.9 -> 74.6Improved
add diffusion layers to ResNet (ablation)ResNet · Pubmed node classificationaccuracy: 70.1 -> 80.1Improved
add internal diffusion layers to convection network (ablation)2-layer residual network · miniImageNet 1-shot, ResNet-18accuracy: 53.04 -> 68.47Improved
put diffusion inside network instead of as Laplacian loss (ablation)2-layer residual network · miniImageNet 1-shot, ResNet-18accuracy: 55.30 -> 68.47Improved
put diffusion inside network instead of as Laplacian loss (ablation)2-layer residual network · CUB 1-shot, ResNet-18accuracy: 70.00 -> 79.12Improved
add internal diffusion layers (ablation)2-layer residual network · miniImageNet 5-shot, ResNet-18accuracy: 79.58 -> 80.02Improved
add internal diffusion layers (ablation)2-layer residual network · miniImageNet 1-shot, WRNaccuracy: 57.07 -> 69.77Improved
use Diff-ResNet instead of label-propagation Diffusion (LaplacianShot-style) (ablation)nearest prototype features · miniImageNet 1-shot, ResNet-18accuracy: 57.81 -> 68.47Improved
increase network depth to 32 layersGCN · Cora/Citeseer/PubmedaccuracyHurt
increase network depth to 32 layersDiff-ResNet · graph benchmarksaccuracyHurt
stack more diffusion layers at fixed total strength (ablation)Diff-ResNet · miniImageNet 1-shotaccuracyNo clear effect

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