Abstract
Node classification on graphs is of great importance in many applications. Due to the limited labeling capability and evolution in real-world open scenarios, novel classes can emerge on unlabeled testing nodes. However, little attention has been paid to novel class discovery on graphs. Discovering novel classes is challenging as novel and known class nodes are correlated by edges, which makes their representations indistinguishable when applying message passing GNNs. Furthermore, the novel classes lack labeling information to guide the learning process. In this paper, we propose a novel method Open-world gRAph neuraL network (ORAL) to tackle these challenges. ORAL first detects correlations between classes through semi-supervised prototypical learning. Inter-class correlations are subsequently eliminated by the prototypical attention network, leading to distinctive representations for different classes. Furthermore, to fully explore multi-scale graph features for alleviating label deficiencies, ORAL generates pseudo-labels by aligning and ensembling label estimations from multiple stacked prototypical attention networks. Extensive experiments on several benchmark datasets show the effectiveness of our proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Brbić, M., Zitnik, M., Wang, S., et al.: Mars: discovering novel cell types across heterogeneous single-cell experiments. Nat. Methods 17, 1200–1206 (2020)
Bruna, J., Zaremba, W., Szlam, A., et al.: Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203 (2013)
Cao, K., Brbic, M., Leskovec, J.: Open-world semi-supervised learning. In: Proceedings of ICLR (2022)
Chen, D., Jacob, L., Mairal, J.: Convolutional kernel networks for graph-structured data. In: Proceedings of ICML (2020)
Ding, K., Wang, J., Li, J., et al.: Graph prototypical networks for few-shot learning on attributed networks. In: Proceedings CIKM (2020)
Gao, X., Hu, W., Guo, Z.: Exploring structure-adaptive graph learning for robust semi-supervised classification. In: Proceedings of ICME (2020)
Geng, C., Huang, S.J., Chen, S.: Recent advances in open set recognition: a survey. In: TPAMI (2020)
Gori, M., Monfardini, G., Scarselli, F.: A new model for learning in graph domains. In: Proceedings of IJCNN. IEEE (2005)
Han, K., Vedaldi, A., Zisserman, A.: Learning to discover novel visual categories via deep transfer clustering. In: Proceedings of ICCV (2019)
Hetzel, L., Fischer, D.S., Günnemann, S., et al.: Graph representation learning for single-cell biology. Current Opinion in Systems Biology (2021)
Huang, W., Zhang, T., Rong, Y., et al.: Adaptive sampling towards fast graph representation learning. In: Proceedings of NeurlIPS (2018)
Izadi, M.R., Fang, Y., Stevenson, R.L., et al.: Optimization of graph neural networks with natural gradient descent. In: Proceedings of IEEE Big Data (2020)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. In: Proceedings of NeurIPS (2016)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of ICLR (2017)
Kuhn, H.W.: The hungarian method for the assignment problem. In: NRL (1955)
Liao, R., Brockschmidt, M., Tarlow, D., et al.: Graph partition neural networks for semi-supervised classification. arXiv preprint arXiv:1803.06272 (2018)
Liu, J., Wang, Y., Zhang, T., et al.: Open-world semi-supervised novel class discovery. In: Proceedings of IJCAI (2023)
Liu, Y., Li, Z., Pan, S., et al.: Anomaly detection on attributed networks via contrastive self-supervised learning. In: IEEE TNNLS (2021)
Lu, B., Gan, X., Yang, L., et al.: Geometer: Graph few-shot class-incremental learning via prototype representation. In: Proceedings of SIGKDD (2022)
Luan, S., Hua, C., Lu, Q., et al.: Is heterophily a real nightmare for graph neural networks on performing node classification? arXiv preprint arXiv:2109.05641 (2021)
Muzio, G., O’Bray, L., Borgwardt, K.: Biological network analysis with deep learning. In: Briefings in bioinformatics (2021)
Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: Proceedings of ICML (2016)
Scarselli, F., Gori, M., Tsoi, A.C., et al.: The graph neural network model. In: IEEE Trans. Neural Netw. (2008)
Shchur, O., Mumme, M., Bojchevski, A., et al.: Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868 (2018)
Sun, X., Yang, Z., Zhang, C., et al.: Conditional gaussian distribution learning for open set recognition. In: Proceedings of CVPR (2020)
Vaze, S., Han, K., Vedaldi, A., et al.: Generalized category discovery. In: Proceedings of CVPR (2022)
Velickovic, P., Cucurull, G., Casanova, A., et al.: Graph attention networks. In: Proceedings of ICLR (2018)
Wen, X., Zhao, B., Qi, X.: Parametric classification for generalized category discovery: a baseline study. In: Proceedings of ICCV (2023)
Wu, M., Pan, S., Zhou, C., et al.: Unsupervised domain adaptive graph convolutional networks. In: Proceedings of WWW (2020)
Wu, M., Pan, S., Zhu, X.: Openwgl: open-world graph learning. In: Proceedings of ICDM (2020)
Yang, Z., Cohen, W., Salakhudinov, R.: Revisiting semi-supervised learning with graph embeddings. In: Proceedings of ICML (2016)
Zhao, B., Wen, X., Han, K.: Learning semi-supervised gaussian mixture models for generalized category discovery. In: Proceedings of ICCV (2023)
Zhong, Z., Zhu, L., Luo, Z., et al.: Openmix: Reviving known knowledge for discovering novel visual categories in an open world. In: Proceedings of CVPR (2021)
Zhu, Y., Xu, Y., Yu, F., et al.: Graph contrastive learning with adaptive augmentation. In: Proceedings of WWW (2021)
Acknowledgement
This work is supported in part by Ant Group, NSF under grant III-2106758, National Natural Science Foundation of China (62276187), and the Shanghai Science, Technology Development Fund No. 22dz1200704.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jin, Y. et al. (2024). Beyond the Known: Novel Class Discovery for Open-World Graph Learning. In: Onizuka, M., et al. Database Systems for Advanced Applications. DASFAA 2024. Lecture Notes in Computer Science, vol 14855. Springer, Singapore. https://doi.org/10.1007/978-981-97-5572-1_8
Download citation
DOI: https://doi.org/10.1007/978-981-97-5572-1_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-5571-4
Online ISBN: 978-981-97-5572-1
eBook Packages: Computer ScienceComputer Science (R0)