AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

CLINIC: Towards High-quality Graph Out-Of-Distribution Detection

Yifan Wang, Haodong Zhang, Changhu Wang, Tao Ren, Dongjie Wang, Wei Ju, Chong Chen, Xian-Sheng Hua, Xiao Luo

ICML 2026 · Graph learning › Graph self-supervised learning · approach: Graph out-of-distribution generalization

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 decision boundary compression loss Lr to Lins+Lcon (ablation)CLINIC · BZR+COX2AUC (%): 80.96 -> 96.32Improved
add decision boundary compression loss Lr to Lins+Lcon (ablation)CLINIC · ClinTox+LIPOAUC (%): 69.35 -> 71.31Improved
add contextual-aware concordance loss Lcon to Lins+Lr (ablation)CLINIC · BZR+COX2AUC (%): 95.73 -> 96.32Improved
add contextual-aware concordance loss Lcon to Lins+Lr (ablation)CLINIC · ClinTox+LIPOAUC (%): 67.93 -> 71.31Improved
add perturbation-aware concordance loss Lins to Lcon+Lr (ablation)CLINIC · BZR+COX2AUC (%): 95.78 -> 96.32Improved
add perturbation-aware concordance loss Lins to Lcon+Lr (ablation)CLINIC · BBBP+BACEAUC (%): 65.80 -> 84.21Improved
use Lr alone versus Lins alone (ablation)CLINIC · BZR+COX2AUC (%): 80.57 -> 94.52Improved
combine two loss components instead of one (ablation)CLINIC · ten ID/OOD pairsAUC (%)Improved
use contextual-affinity graph and twin concordance learning versus GOOD-DCLINIC · ten ID/OOD pairsaverage AUC: +1.16% over HGOE, +2.65% over GOOD-DImproved
set k2 too small or too close to k1 in affinity graph (ablation)CLINIC · Figure 3 dataset pairsAUCHurt
use too many reciprocal neighbors k (ablation)CLINIC · Figure 4 dataset pairsAUCHurt
vary number of clusters C (ablation)CLINIC · Figure 4 dataset pairsAUCNo 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