AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning

Qirui Ji, Bin Qin, Yifan Jin, Yunze Zhao, Chuxiong Sun, Changwen Zheng, Jianwen Cao, Jiangmeng Li

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Graph contrastive learning analysis · 0 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
integrate multiple ring granularities (6, 9, 12) instead of a single ring size (ablation)HTG-GCL · NCI1, MUTAG, IMDB-B, IMDB-M (unsupervised)accuracy (%): 79.3 -> 80.7 (NCI1, ring 6 vs full)Improved
add multi-granularity decoupled contrast with uncertainty weighting (MGDC) (ablation)HTG-GCL with three granularities · NCI1 (unsupervised)accuracy (%): 79.7 -> 80.7Improved
add MGDC (ablation)HTG-GCL with three granularities · IMDB-M (unsupervised)accuracy (%): 50.9 -> 51.5Improved
add MGDC to two-granularity variant (ring 9, 12) (ablation)HTG-GCL two granularities · NCI1 (unsupervised)accuracy (%): 80.1 -> 79.8Hurt
add MGDC to two-granularity variant (ring 6, 9) (ablation)HTG-GCL two granularities · MUTAG (unsupervised)accuracy (%): 89.9 -> 90.1Improved
use four granularities (6,9,12,15) instead of three (ablation)HTG-GCL · NCI1 and NCI109accuracyHurt
set decoupled loss coefficient beta to 0.01 (ablation)HTG-GCL · NCI1 and NCI109accuracyImproved
use HTG-GCL instead of CellCLATunsupervised graph classification · TU datasetsaccuracy (%): 79.4 -> 80.7 (NCI1); 50.6 -> 51.5 (IMDB-M)Improved
use HTG-GCL in semi-supervised setting instead of CellCLAT10% labels with pseudo-labeling · TU datasetsaccuracy (%): 69.5 -> 70.6 (NCI109)Improved
increase batch size up to 128 (ablation)HTG-GCL · NCI1 and NCI109 (20 epochs)accuracyImproved

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