{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T01:51:49Z","timestamp":1777341109264,"version":"3.51.4"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shanghai Pujiang Program","award":["24PJA004"],"award-info":[{"award-number":["24PJA004"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2232025D-33"],"award-info":[{"award-number":["2232025D-33"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3584090","type":"journal-article","created":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:19:43Z","timestamp":1752103183000},"page":"19255-19269","source":"Crossref","is-referenced-by-count":5,"title":["Enhancing Graph Neural Networks for Out-of-Distribution Graph Detection"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6009-780X","authenticated-orcid":false,"given":"Ge","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Donghua University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6588-3014","authenticated-orcid":false,"given":"Zhenyu","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1371-5801","authenticated-orcid":false,"given":"Jia","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1049-1002","authenticated-orcid":false,"given":"Pengfei","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4408-1952","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"ref2","first-page":"4805","article-title":"Hierarchical graph representation learning with differentiable pooling","volume-title":"Proc. NeurIPS","author":"Ying"},{"key":"ref3","article-title":"How powerful are graph neural networks","volume-title":"Proc. ICLR","author":"Xu"},{"key":"ref4","first-page":"2083","article-title":"Graph U-Nets","volume-title":"Proc. ICML","author":"Gao"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3173318"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3129649"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3266243"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3695863"},{"key":"ref11","first-page":"30277","article-title":"GraphDE: A generative framework for debiased learning and out-of-distribution detection on graphs","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref12","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. ICLR","author":"Hendrycks"},{"key":"ref13","first-page":"37199","article-title":"Is out-of-distribution detection learnable?","volume-title":"Proc. NeurIPS","author":"Fang"},{"key":"ref14","article-title":"Generalized out-of-distribution detection: A survey","author":"Yang","year":"2021","journal-title":"arXiv:2110.11334"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3231924"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3189996"},{"key":"ref17","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016","journal-title":"arXiv:1606.06565"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3112897"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3271856"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/s21144758"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3054306"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599244"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29480"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref26","first-page":"20827","article-title":"Out-of-distribution detection with deep nearest neighbors","volume-title":"Proc. ICML","author":"Sun"},{"key":"ref27","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. NeurIPS","author":"Lee"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3695863"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3190922"},{"key":"ref30","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. ICLR","author":"Kipf"},{"key":"ref31","article-title":"Graph attention networks","volume-title":"Proc. ICLR","author":"Veli\u010dkovi\u0107"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3157688"},{"key":"ref33","first-page":"3734","article-title":"Self-attention graph pooling","volume-title":"Proc. ICML","author":"Lee"},{"issue":"9","key":"ref34","first-page":"12","article-title":"The reduction of a graph to canonical form and the algebra which appears therein","volume":"2","author":"Weisfeiler","year":"1968","journal-title":"NTI, Ser."},{"key":"ref35","article-title":"A survey on the expressive power of graph neural networks","author":"Sato","year":"2020","journal-title":"arXiv:2003.04078"},{"key":"ref36","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. ICML","author":"Gilmer"},{"key":"ref37","article-title":"From stars to subgraphs: Uplifting any GNN with local structure awareness","volume-title":"Proc. ICLR","author":"Zhao"},{"key":"ref38","first-page":"599","article-title":"Breaking the limits of message passing graph neural networks","volume-title":"Proc. ICML","author":"Balcilar"},{"key":"ref39","first-page":"2153","article-title":"Provably powerful graph networks","volume-title":"Proc. NeurIPS","volume":"32","author":"Maron"},{"key":"ref40","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","volume-title":"Proc. ICLR","author":"Liang"},{"key":"ref41","article-title":"Deep anomaly detection with outlier exposure","volume-title":"Proc. ICLR","author":"Hendrycks"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01096"},{"key":"ref43","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. NeurIPS","author":"Liu"},{"key":"ref44","article-title":"A tutorial on energy-based learning","volume":"1","author":"LeCun","year":"2006","journal-title":"Predicting Structured Data"},{"key":"ref45","article-title":"Contrastive training for improved out-of-distribution detection","author":"Winkens","year":"2020","journal-title":"arXiv:2007.05566"},{"key":"ref46","first-page":"569","article-title":"Variational-and metric-based deep latent space for out-of-distribution detection","volume-title":"Proc. UAI","author":"Dinari"},{"issue":"1","key":"ref47","first-page":"49","article-title":"On the generalized distance in statistics","volume":"2","author":"Mahalanobis","year":"1936","journal-title":"Proc. Nat. Inst. Sci. India"},{"key":"ref48","article-title":"SSD: A unified framework for self-supervised outlier detection","volume-title":"Proc. ICLR","author":"Sehwag"},{"key":"ref49","first-page":"18033","article-title":"Graph posterior network: Bayesian predictive uncertainty for node classification","volume-title":"Proc. NeurIPS","author":"Stadler"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539457"},{"key":"ref51","first-page":"12827","article-title":"Uncertainty aware semi-supervised learning on graph data","volume-title":"Proc. NeurIPS","author":"Zhao"},{"key":"ref52","article-title":"Energy-based out-of-distribution detection for graph neural networks","volume-title":"Proc. ICLR","author":"Wu"},{"key":"ref53","first-page":"30457","article-title":"Graph neural stochastic diffusion for estimating uncertainty in node classification","volume-title":"Proc. ICML","author":"Lin"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736983"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714879"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570446"},{"key":"ref57","first-page":"1448","article-title":"Invariant rationalization","volume-title":"Proc. ICML","author":"Chang"},{"key":"ref58","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9878-1_4"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/BF00532240"},{"key":"ref62","first-page":"5769","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. NeurIPS","volume":"30","author":"Gulrajani"},{"key":"ref63","first-page":"1608","article-title":"Learning generative models with Sinkhorn divergences","volume-title":"Proc. AISTATS","author":"Genevay"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220024"},{"key":"ref65","first-page":"4202","article-title":"Understanding attention and generalization in graph neural networks","volume-title":"Proc. NeurIPS","author":"Knyazev"},{"key":"ref66","article-title":"Discovering invariant rationales for graph neural networks","volume-title":"Proc. ICLR","author":"Wu"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3193725"},{"key":"ref68","article-title":"DrugOOD: Out-of-distribution (OOD) dataset curator and benchmark for AI-aided drug discovery\u2014A focus on affinity prediction problems with noise annotations","author":"Ji","year":"2022","journal-title":"arXiv:2201.09637"},{"key":"ref69","article-title":"TUDataset: A collection of benchmark datasets for learning with graphs","author":"Morris","year":"2020","journal-title":"arXiv:2007.08663"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679710"},{"key":"ref71","article-title":"Fast graph representation learning with PyTorch geometric","author":"Fey","year":"2019","journal-title":"arXiv:1903.02428"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/335191.335388"},{"key":"ref73","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11074755.pdf?arnumber=11074755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:38:28Z","timestamp":1759945108000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11074755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":74,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3584090","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}