{"type":"ScholarlyArticle","title":"G2Pxy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns","authors":[{"name":"Qin Zhang","slug":"qin-zhang","given":"Qin","family":"Zhang","affiliation":"Big Data Institute , College of Computer Science and Software Engineering , Shenzhen University , China"},{"name":"Zelin Shi","slug":"zelin-shi","given":"Zelin","family":"Shi","affiliation":"Big Data Institute , College of Computer Science and Software Engineering , Shenzhen University , China"},{"name":"Xiaolin Zhang","slug":"xiaolin-zhang","given":"Xiaolin","family":"Zhang","affiliation":"Sensetime"},{"name":"Xiaojun Chen","slug":"xiaojun-chen","given":"Xiaojun","family":"Chen","affiliation":"Big Data Institute , College of Computer Science and Software Engineering , Shenzhen University , China"},{"name":"Philippe Fournier-Viger","slug":"philippe-fournier-viger","given":"Philippe","family":"Fournier-Viger","affiliation":"Big Data Institute , College of Computer Science and Software Engineering , Shenzhen University , China"},{"name":"Shirui Pan","slug":"shirui-pan","given":"Shirui","family":"Pan","affiliation":"School of Information and Communication Technology , Griffith University , Queensland , Australia"}],"abstract":"Node classification is the task of predicting the labels of unlabeled nodes in a graph. State-of-the-art methods based on graph neural networks achieve  excellent performance when all labels are available\r\n during training. But in real-life, models are of ten applied on data with new classes, which can lead to massive misclassification and thus significantly degrade performance. Hence, developing\r\n open-set classification methods is crucial to determine if a given sample belongs to a known class. Existing methods for open-set node classification generally use transductive learning with part or all\r\n of the features of real unseen class nodes to help with open-set classification. In this paper, we propose a novel generative open-set node classification method, i.e., G2Pxy, which follows a stricter inductive learning setting where no information about unknown classes is available during training and validation. Two kinds of proxy unknown nodes, inter-class unknown proxies and external unknown proxies are generated via mixup to efficiently anticipate the distribution of novel classes. Using the generated proxies, a closed-set classifier can be transformed into an open-set one, by augmenting it with an extra proxy classifier. Under the constraints\r\n of both cross entropy loss and complement entropy loss, G2Pxy achieves superior effectiveness for unknown class detection and known class classification, which is validated by experiments on bench\r\nmark graph datasets. Moreover, G2Pxy does not have specific requirement on the GNN architecture and shows good generalizations.","doi":"10.24963/ijcai.2023/509","url":"https://ijcai.org/proceedings/2023/509","pdf":"https://ijcai.org/proceedings/2023/0509.pdf","markdown":"https://ijcai.org/proceedings/2023/509.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/509","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Machine Learning","track":"Main Track","number":509,"pages":{"first":4576,"last":4583},"keywords":["Machine Learning: ML: Classification","Data Mining: DM: Mining graphs"],"videos":[],"references":[{"position":1,"raw":"[Bendale and Boult, 2016] Abhijit Bendale and Terrance E Boult. Towards open set deep networks. In IEEE con- ference on computer vision and pattern recognition, pages 1563-1572, 2016.","title":"Towards open set deep networks","authors":"Abhijit Bendale, Terrance E Boult","year":"2016","venue":"IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2018] Hao-Yun Chen, Pei-Hsin Wang, Chun- Hao Liu, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, and Da-Cheng Juan. Complement objective training. In International Conference on Learning Rep- resentations, 2018.","title":"Complement objective training","authors":"Pei-Hsin Hao-Yun Chen, Chun-Hao Wang, Shih-Chieh Liu, Jia-Yu Chang, Yu-Ting Pan, Wei Chen, Da-Cheng Wei, Juan","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ge et al., 2017] ZongYuan Ge, Sergey Demyanov, Zetao Chen, and Rahil Garnavi. Generative openmax for multi- class open set classification. In British Machine Vision Conference. BMVA Press, 2017.","title":"Generative openmax for multi-class open set classification","authors":"Ge","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Guo et al., 2017] Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q Weinberger. On calibration of modern neural net- works. In International conference on machine learning, pages 1321-1330, 2017.","title":"On calibration of modern neural networks","authors":"Chuan Guo, Geoff Pleiss, Yu Sun, Kilian Q Weinberger","year":"2017","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Hamilton et al., 2017] Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. Neural information processing systems, 30, 2017.","title":"Inductive representation learning on large graphs","authors":"Hamilton","year":"2017","venue":"Neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Han et al., 2022] Xiaotian Han, Zhimeng Jiang, Ninghao Liu, and Xia Hu. G-mixup: Graph data augmentation for graph classification. In International Conference on Ma- chine Learning, pages 8230-8248. PMLR, 2022.","title":"G-mixup: Graph data augmentation for graph classification","authors":"Xiaotian Han, Zhimeng Jiang, Ninghao Liu, Xia Hu","year":"2022","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hein et al., 2019] Matthias Hein, Maksym An- driushchenko, and Julian Bitterwolf. Why relu networks yield high-confidence predictions far away from the train- ing data and how to mitigate the problem. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 41-50, 2019.","title":"Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem","authors":"Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf","year":"2019","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hendrycks and Gimpel, 2017] Dan Hendrycks and Kevin Gimpel. A baseline for detecting misclassified and out- of-distribution examples in neural networks. International Conference on Learning Representations, 2017.","title":"A baseline for detecting misclassified and outof-distribution examples in neural networks","authors":"Gimpel Hendrycks, Dan Hendrycks, Kevin Gimpel","year":"2017","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kipf and Welling, 2017] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Rep- resentations, 2017.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2017","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Liu et al., 2021] Zemin Liu, Yuan Fang, Chenghao Liu, and Steven CH Hoi. Relative and absolute location embedding for few-shot node classification on graph. In AAAI Con- ference on Artificial Intelligence, volume 35, pages 4267- 4275, 2021.","title":"Relative and absolute location embedding for few-shot node classification on graph","authors":"Zemin Liu, Yuan Fang, Chenghao Liu, Steven Ch Hoi","year":"2021","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Neal et al., 2018] Lawrence Neal, Matthew Olson, Xiaoli Fern, Weng-Keen Wong, and Fuxin Li. Open set learn- ing with counterfactual images. In European Conference on Computer Vision, pages 613-628, 2018.","title":"Open set learning with counterfactual images","authors":"Lawrence Neal, Matthew Olson, Xiaoli Fern, Weng-Keen Wong, Fuxin Li","year":"2018","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Perera et al., 2020] Pramuditha Perera, Vlad I Morariu, Ra- jiv Jain, Varun Manjunatha, Curtis Wigington, Vicente Ordonez, and Vishal M Patel. Generative-discriminative feature representations for open-set recognition. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11814-11823, 2020.","title":"Generative-discriminative feature representations for open-set recognition","authors":"Perera","year":"2020","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Scheirer et al., 2012] Walter J Scheirer, Anderson de Rezende Rocha, Archana Sapkota, and Terrance E Boult. Toward open set recognition. IEEE transac- tions on pattern analysis and machine intelligence, 35(7):1757-1772, 2012.","title":"Toward open set recognition","authors":"J Walter, Anderson Scheirer, De Rezende, Archana Rocha, Terrance E Sapkota, Boult","year":"2012","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Shu et al., 2017] Lei Shu, Hu Xu, and Bing Liu. Doc: Deep open classification of text documents. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2911-2916, 2017.","title":"Doc: Deep open classification of text documents","authors":"Lei Shu, Hu Xu, Bing Liu","year":"2017","venue":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Tang et al., 2021] Yan Tang, Zhijin Zhao, Chun Li, and Xueyi Ye. Open set recognition algorithm based on con- ditional gaussian encoder. Mathematical Biosciences and Engineering, 18(5):6620-6637, 2021.","title":"Open set recognition algorithm based on conditional gaussian encoder","authors":"Yan Tang, Zhijin Zhao, Chun Li, Xueyi Ye","year":"2021","venue":"Mathematical Biosciences and Engineering","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Veličković et al., 2018] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. Graph attention networks. In Interna- tional Conference on Learning Representations, 2018.","title":"Graph attention networks","authors":"Veličković","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Verma et al., 2019] Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez- Paz, and Yoshua Bengio. Manifold mixup: Better rep- resentations by interpolating hidden states. In Interna- tional Conference on Machine Learning, pages 6438- 6447, 2019.","title":"Manifold mixup: Better representations by interpolating hidden states","authors":"Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz, Yoshua Bengio","year":"2019","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wang et al., 2020] Zifeng Wang, Batool Salehi, Andrey Gritsenko, Kaushik Chowdhury, Stratis Ioannidis, and Jen- nifer Dy. Open-world class discovery with kernel net- works. In IEEE International Conference on Data Mining, pages 631-640, 2020.","title":"Open-world class discovery with kernel networks","authors":"Wang","year":"2020","venue":"IEEE International Conference on Data Mining","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wong et al., 2021] Randy Yee Man Wong, Christy MK Cheung, Bo Xiao, and Jason Bennett Thatcher. Standing up or standing by: Understanding bystanders' proactive re- porting responses to social media harassment. Information Systems Research, 32(2):561-581, 2021.","title":"Standing up or standing by: Understanding bystanders' proactive reporting responses to social media harassment","authors":"Randy Yee, Man Wong, Christy Mk Cheung, Bo Xiao, Jason Bennett Thatcher","year":"2021","venue":"Information Systems Research","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wu et al., 2020] Man Wu, Shirui Pan, and Xingquan Zhu. Openwgl: Open-world graph learning. In IEEE interna- tional conference on data mining, pages 681-690, 2020.","title":"Openwgl: Open-world graph learning","authors":"Wu","year":"2020","venue":"IEEE international conference on data mining","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wu et al., 2021] Man Wu, Shirui Pan, and Xingquan Zhu. Openwgl: open-world graph learning for unseen class node classification. Knowledge and Information Systems, pages 1-26, 2021.","title":"Openwgl: open-world graph learning for unseen class node classification","authors":"Wu","year":"2021","venue":"Knowledge and Information Systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Yu et al., 2017] Yang Yu, Wei-Yang Qu, Nan Li, and Zimin Guo. Open-category classification by adversarial sample generation. In International Joint Conference on Artificial Intelligence, pages 3357-3363, 2017.","title":"Open-category classification by adversarial sample generation","authors":"Yang Yu, Wei-Yang Qu, Nan Li, Zimin Guo","year":"2017","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2017/469"},{"position":23,"raw":"[Zheng et al., 2020] Chuanpan Zheng, Xiaoliang Fan, Cheng Wang, and Jianzhong Qi. Gman: A graph multi-attention network for traffic prediction. In AAAI Conference on Artificial Intelligence, volume 34, pages 1234-1241, 2020.","title":"Gman: A graph multi-attention network for traffic prediction","authors":"Zheng","year":"2020","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhou et al., 2021] Da-Wei Zhou, Han-Jia Ye, and De- Chuan Zhan. Learning placeholders for open-set recog- nition. In the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4401-4410, 2021.","title":"Learning placeholders for open-set recognition","authors":"Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan","year":"2021","venue":"the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhu et al., 2022] Qi Zhu, Chao Zhang, Chanyoung Park, Carl Yang, and Jiawei Han. Shift-robust node classifi- cation via graph adversarial clustering. arXiv preprint arXiv:2203.15802, 2022.","title":"Shift-robust node classification via graph adversarial clustering","authors":"Qi Zhu, Chao Zhang, Chanyoung Park, Carl Yang, Jiawei Han","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}