AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Label Efficient Regularization and Propagation for Graph Node Classification

Tian Xie, Rajgopal Kannan, C.‐C. Jay Kuo

TPAMI 2023 · 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
replace GraphHop with LERP (reliable pseudo-labels, more label iterations)GraphHop · Cora (1 label/class)test accuracy (%): 59.12 -> 72.47Improved
replace GraphHop with LERPGraphHop · Amazon Photo (2 labels/class)test accuracy (%): 70.86 -> 83.10Improved
replace GraphHop with LERPGraphHop · Coauthor CS (1 label/class)test accuracy (%): 65.03 -> 82.46Improved
replace GraphHop with LERP at standard label rateGraphHop · Cora (20 labels/class)test accuracy (%): 81.05 -> 82.65Improved
LERP versus APPNP at 16 labels/classAPPNP · PubMed (16 labels/class)test accuracy (%): 79.17 -> 77.20Hurt
add LR classifier training (LERP vs LERP-V with U_alpha=0) (ablation)LERP · five datasets, various label ratestest accuracy (%)Improved
increase label-embedding iterations max_iter from 0 (GraphHop-like) to up to 20 (ablation)LERP · five datasets, various label ratestest accuracy (%)Improved
increase sharpening temperature T above 1 (ablation)LERP · CiteSeer (1 label/class)test accuracy (%)No clear effect
small sharpening temperature T (ablation)LERP · CiteSeer (1 label/class)test accuracy (%)Hurt
slightly increase alpha and beta (ablation)LERP · CiteSeer (1 label/class)test accuracy (%)Improved
use 20 alternate rounds instead of 100 (ablation)LERP · five datasets (20 labels/class)test accuracy (%)No clear effect
apply LERP to kNN graph of images instead of GCNGCN · COIL20 (1 label/class)test accuracy (%): 61.05 -> 86.75Improved

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