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
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:132464-132478, 2026.

Abstract

This paper studies the problem of graph out-of-distribution (OOD) detection, which aims to identify anomaly graphs out of a graph dataset. Prior efforts usually focus on the utilization of topological structures with unsupervised graph learning to foster typical pattern recognition, which overlooks the semantic structure preserved in contextually affine neighborhoods. Towards this end, we propose a novel approach named Contextual Affinity Exploration with Twin Concordance (CLINIC) for graph OOD detection. The core of CLINIC is to explore and exploit the contextual affinity of the graph data samples for discriminative graph representations. In particular, our CLINIC first builds a contextual affinity graph to depict the semantic structure in the hidden space. More importantly, we introduce high-order affinity to enhance geometric understanding of the structure by utilizing a meta-graph neural network. To enhance representation discriminability with high robustness, we introduce twin concordance learning, which not only minimizes the difference of affinity distributions across different views, but also encourages the consistency between contextually affinitive neighbors. Finally, we introduce a compression strategy to expand the decision boundary for enhanced separation between in-distribution and out-of-distribution graphs. Extensive experimental results demonstrate the superiority of our CLINIC across ten real datasets in comparison to various baselines.

Cite this Paper


BibTeX
@InProceedings{pmlr-v306-wang26kt, title = {{CLINIC}: Towards High-quality Graph Out-Of-Distribution Detection}, author = {Wang, Yifan and Zhang, Haodong and Wang, Changhu and Ren, Tao and Wang, Dongjie and Ju, Wei and Chen, Chong and Hua, Xian-Sheng and Luo, Xiao}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {132464--132478}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/wang26kt/wang26kt.pdf}, url = {https://proceedings.mlr.press/v306/wang26kt.html}, abstract = {This paper studies the problem of graph out-of-distribution (OOD) detection, which aims to identify anomaly graphs out of a graph dataset. Prior efforts usually focus on the utilization of topological structures with unsupervised graph learning to foster typical pattern recognition, which overlooks the semantic structure preserved in contextually affine neighborhoods. Towards this end, we propose a novel approach named Contextual Affinity Exploration with Twin Concordance (CLINIC) for graph OOD detection. The core of CLINIC is to explore and exploit the contextual affinity of the graph data samples for discriminative graph representations. In particular, our CLINIC first builds a contextual affinity graph to depict the semantic structure in the hidden space. More importantly, we introduce high-order affinity to enhance geometric understanding of the structure by utilizing a meta-graph neural network. To enhance representation discriminability with high robustness, we introduce twin concordance learning, which not only minimizes the difference of affinity distributions across different views, but also encourages the consistency between contextually affinitive neighbors. Finally, we introduce a compression strategy to expand the decision boundary for enhanced separation between in-distribution and out-of-distribution graphs. Extensive experimental results demonstrate the superiority of our CLINIC across ten real datasets in comparison to various baselines.} }
Endnote
%0 Conference Paper %T CLINIC: Towards High-quality Graph Out-Of-Distribution Detection %A Yifan Wang %A Haodong Zhang %A Changhu Wang %A Tao Ren %A Dongjie Wang %A Wei Ju %A Chong Chen %A Xian-Sheng Hua %A Xiao Luo %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-wang26kt %I PMLR %P 132464--132478 %U https://proceedings.mlr.press/v306/wang26kt.html %V 306 %X This paper studies the problem of graph out-of-distribution (OOD) detection, which aims to identify anomaly graphs out of a graph dataset. Prior efforts usually focus on the utilization of topological structures with unsupervised graph learning to foster typical pattern recognition, which overlooks the semantic structure preserved in contextually affine neighborhoods. Towards this end, we propose a novel approach named Contextual Affinity Exploration with Twin Concordance (CLINIC) for graph OOD detection. The core of CLINIC is to explore and exploit the contextual affinity of the graph data samples for discriminative graph representations. In particular, our CLINIC first builds a contextual affinity graph to depict the semantic structure in the hidden space. More importantly, we introduce high-order affinity to enhance geometric understanding of the structure by utilizing a meta-graph neural network. To enhance representation discriminability with high robustness, we introduce twin concordance learning, which not only minimizes the difference of affinity distributions across different views, but also encourages the consistency between contextually affinitive neighbors. Finally, we introduce a compression strategy to expand the decision boundary for enhanced separation between in-distribution and out-of-distribution graphs. Extensive experimental results demonstrate the superiority of our CLINIC across ten real datasets in comparison to various baselines.
APA
Wang, Y., Zhang, H., Wang, C., Ren, T., Wang, D., Ju, W., Chen, C., Hua, X. & Luo, X.. (2026). CLINIC: Towards High-quality Graph Out-Of-Distribution Detection. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:132464-132478 Available from https://proceedings.mlr.press/v306/wang26kt.html.

Related Material