AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Semi-Supervised Hierarchical Graph Classification

Jia Li, Yongfeng Huang, Heng Chang, Yu Rong

TPAMI 2022 · Graph learning › Graph self-supervised learning · approach: Heterophily and imbalance on graphs · 37 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 cautious iterative pseudo-label enlargement (SEAL to SEAL-CI) (ablation)SEAL · Synthetic hierarchical graphaccuracy: 87.8% -> 91.2%Improved
add cautious iterative pseudo-label enlargement (ablation)SEAL · arXiv paper dataaccuracy: 78.8% -> 79.4%Improved
add cautious iterative pseudo-label enlargement (ablation)SEAL · Tencent QQ group dataMacro-F1: 84.3% -> 85.5%Improved
use hierarchical graph connections (Bert-HC) instead of independent classification (Bert-IC)Bert features · arXiv paper dataaccuracy: 70.1% -> 75.2%Improved
add graph instance structure to Bert features (Bert-IC vs Bert-MLP)Bert features · arXiv paper dataaccuracy: 63.7% -> 70.1%Improved
use HGMI-based SEAL instead of SAGE ignoring hierarchySAGE · Tencent QQ group dataMacro-F1: 75.0% -> 84.3%Improved
use SEAL instead of MIRACLEMIRACLE · Tencent QQ group dataMacro-F1: 80.3% -> 84.3%Improved
use supervised embeddings (SAGE) instead of unsupervised graph2vecgraph2vec-GCN · Synthetic hierarchical graphaccuracy: 85.2% -> 85.7%Improved
increase lambda (number of pseudo-labels) in SEAL-CI (ablation)SEAL-CI · Tencent QQ group datafalse prediction rate: 2.4%Hurt
use kernel methods instead of embedding methodsGK-SVM/WL-SVM · arXiv paper dataaccuracy: 38.7% -> 35.1%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