AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

ReCoG: Relational and Compact Context Graph Learning for Few-shot Molecular Property Prediction

Zeyu Wang, Xin Zheng, Yao Lu, Shanqing Yu, Qi Xuan, Shirui Pan

ICML 2026 · Graph learning › Graph self-supervised learning · approach: Molecular graph pretraining · 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
add CPRL and CGIB (ablation)ReCoG · Tox21 10-shotROC-AUC (%): 90.21 -> 93.52Improved
add CPRL and CGIB (ablation)ReCoG · Tox21 1-shotROC-AUC (%): 86.91 -> 91.01Improved
add CPRL and CGIB (ablation)ReCoG · SIDER 1-shotROC-AUC (%): 86.93 -> 90.06Improved
add CPRL (cross-property relation learning) (ablation)ReCoG · Tox21 1-shotROC-AUC (%): 88.18 -> 91.01Improved
add CPRL (cross-property relation learning) (ablation)ReCoG · SIDER 10-shotROC-AUC (%): 91.60 -> 93.98Improved
add CGIB (context graph information bottleneck) (ablation)ReCoG · Tox21 1-shotROC-AUC (%): 90.28 -> 91.01Improved
add CGIB (context graph information bottleneck) (ablation)ReCoG · SIDER 10-shotROC-AUC (%): 91.54 -> 93.98Improved
use MSE instead of BCE for CPRL relation loss (ablation)ReCoG · Tox21 1-shotROC-AUC (%): 88.79 -> 91.01Improved
use MSE instead of BCE for CPRL relation loss (ablation)ReCoG · SIDER 1-shotROC-AUC (%): 87.71 -> 90.06Improved
set Gumbel-Sigmoid temperature t to 1.0 instead of 0.1 (ablation)ReCoG · Tox21 10-shotROC-AUC (%): 89.37 -> 93.52Improved
raise Gumbel-Sigmoid temperature t from 1.0 to 2.0 (ablation)ReCoG · Tox21 10-shotROC-AUC (%): 93.52 -> 91.47Hurt
set Gumbel-Sigmoid temperature t to 1.0 instead of 0.1 (ablation)ReCoG · SIDER 1-shotROC-AUC (%): 85.44 -> 90.06Improved

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