ABSTRACT
Graph neural networks (GNNs) have achieved strong performance in various applications. In the real world, network data is usually formed in a streaming fashion. The distributions of patterns that refer to neighborhood information of nodes may shift over time. The GNN model needs to learn the new patterns that cannot yet be captured. But learning incrementally leads to the catastrophic forgetting problem that historical knowledge is overwritten by newly learned knowledge. Therefore, it is important to train GNN model to learn new patterns and maintain existing patterns simultaneously, which few works focus on. In this paper, we propose a streaming GNN model based on continual learning so that the model is trained incrementally and up-to-date node representations can be obtained at each time step. Firstly, we design an approximation algorithm to detect new coming patterns efficiently based on information propagation. Secondly, we combine two perspectives of data replaying and model regularization for existing pattern consolidation. Specially, a hierarchy-importance sampling strategy for nodes is designed and a weighted regularization term for GNN parameters is derived, achieving greater stability and generalization of knowledge consolidation. Our model is evaluated on real and synthetic data sets and compared with multiple baselines. The results of node classification prove that our model can efficiently update model parameters and achieve comparable performance to model retraining. In addition, we also conduct a case study on the synthetic data, and carry out some specific analysis for each part of our model, illustrating its ability to learn new knowledge and maintain existing knowledge from different perspectives.
Supplemental Material
- Rahaf Aljundi, Francesca Babiloni, Mohamed Elhoseiny, Marcus Rohrbach, and Tinne Tuytelaars. 2018. Memory aware synapses: Learning what (not) to forget. In Proceedings of the European Conference on Computer Vision (ECCV). 139--154.Google ScholarDigital Library
- Rahaf Aljundi, Klaas Kelchtermans, and Tinne Tuytelaars. 2019 a. Task-free continual learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 11254--11263.Google ScholarCross Ref
- Rahaf Aljundi, Min Lin, Baptiste Goujaud, and Yoshua Bengio. 2019 b. Online continual learning with no task boundaries. arXiv preprint arXiv:1903.08671 (2019).Google Scholar
- Songgaojun Deng, Huzefa Rangwala, and Yue Ning. 2019. Learning Dynamic Context Graphs for Predicting Social Events. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1007--1016.Google ScholarDigital Library
- Lun Du, Yun Wang, Guojie Song, Zhicong Lu, and Junshan Wang. 2018. Dynamic Network Embedding: An Extended Approach for Skip-gram based Network Embedding. In IJCAI. 2086--2092.Google Scholar
- Santo Fortunato. 2010. Community detection in graphs. Physics reports, Vol. 486, 3--5 (2010), 75--174.Google Scholar
- Edgar N Gilbert. 1959. Random graphs. The Annals of Mathematical Statistics, Vol. 30, 4 (1959), 1141--1144.Google ScholarCross Ref
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems. 1025--1035.Google Scholar
- Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).Google Scholar
- James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al. 2017. Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences, Vol. 114, 13 (2017), 3521--3526.Google ScholarCross Ref
- Jundong Li, Harsh Dani, Xia Hu, Jiliang Tang, Yi Chang, and Huan Liu. 2017. Attributed network embedding for learning in a dynamic environment. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. ACM, 387--396.Google ScholarDigital Library
- Xi Liu, Ping-Chun Hsieh, Nick Duffield, Rui Chen, Muhe Xie, and Xidao Wen. 2018. Streaming Network Embedding through Local Actions. arXiv preprint arXiv:1811.05932 (2018).Google Scholar
- David Lopez-Paz and Marc'Aurelio Ranzato. 2017. Gradient episodic memory for continual learning. In Advances in Neural Information Processing Systems. 6467--6476.Google Scholar
- Yao Ma, Ziyi Guo, Zhaochun Ren, Eric Zhao, Jiliang Tang, and Dawei Yin. 2018. Streaming Graph Neural Networks. arXiv preprint arXiv:1810.10627 (2018).Google Scholar
- Arun Mallya and Svetlana Lazebnik. 2018. Packnet: Adding multiple tasks to a single network by iterative pruning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7765--7773.Google ScholarCross Ref
- Andrew Kachites McCallum, Kamal Nigam, Jason Rennie, and Kristie Seymore. 2000. Automating the construction of internet portals with machine learning. Information Retrieval, Vol. 3, 2 (2000), 127--163.Google ScholarDigital Library
- Cuong V Nguyen, Yingzhen Li, Thang D Bui, and Richard E Turner. 2017. Variational continual learning. arXiv preprint arXiv:1710.10628 (2017).Google Scholar
- Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, and Charles E Leisersen. 2019. Evolvegcn: Evolving graph convolutional networks for dynamic graphs. arXiv preprint arXiv:1902.10191 (2019).Google Scholar
- Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 701--710.Google ScholarDigital Library
- Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H Lampert. 2017. icarl: Incremental classifier and representation learning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2001--2010.Google ScholarCross Ref
- Tom Schaul, John Quan, Ioannis Antonoglou, and David Silver. 2015. Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015).Google Scholar
- Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. 2017. Continual learning with deep generative replay. In Advances in Neural Information Processing Systems. 2990--2999.Google ScholarDigital Library
- Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. 2015. Line: Large-scale information network embedding. In Proceedings of the 24th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 1067--1077.Google ScholarDigital Library
- Jie Tang, Jing Zhang, Limin Yao, Juanzi Li, Li Zhang, and Zhong Su. 2008. Arnetminer: extraction and mining of academic social networks. In Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 990--998.Google ScholarDigital Library
- Guillem Velivc ković, Petar any Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).Google Scholar
- Jeffrey S Vitter. 1985. Random sampling with a reservoir. ACM Transactions on Mathematical Software (TOMS), Vol. 11, 1 (1985), 37--57.Google ScholarDigital Library
- Junshan Wang, Yilun Jin, Guojie Song, and Xiaojun Ma. [n.d.]. EPNE: Evolutionary Pattern Preserving Network Embedding. ( [n.,d.]).Google Scholar
- Geoffrey I Webb, Roy Hyde, Hong Cao, Hai Long Nguyen, and Francois Petitjean. 2016. Characterizing concept drift. Data Mining and Knowledge Discovery, Vol. 30, 4 (2016), 964--994.Google ScholarDigital Library
- Mark Weber, Giacomo Domeniconi, Jie Chen, Daniel Karl I Weidele, Claudio Bellei, Tom Robinson, and Charles E Leiserson. 2019. Anti-money laundering in bitcoin: Experimenting with graph convolutional networks for financial forensics. arXiv preprint arXiv:1908.02591 (2019).Google Scholar
- Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How Powerful are Graph Neural Networks? arXiv preprint arXiv:1810.00826 (2018).Google Scholar
- Sijie Yan, Yuanjun Xiong, and Dahua Lin. 2018. Spatial temporal graph convolutional networks for skeleton-based action recognition. In Thirty-second AAAI conference on artificial intelligence.Google ScholarCross Ref
- Haiyan Yin and Sinno Jialin Pan. 2017. Knowledge transfer for deep reinforcement learning with hierarchical experience replay. In Thirty-First AAAI Conference on Artificial Intelligence.Google ScholarDigital Library
- Friedemann Zenke, Ben Poole, and Surya Ganguli. 2017. Continual learning through synaptic intelligence. In Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 3987--3995.Google ScholarDigital Library
- Lekui Zhou, Yang Yang, Xiang Ren, Fei Wu, and Yueting Zhuang. 2018. Dynamic network embedding by modeling triadic closure process. In Thirty-Second AAAI Conference on Artificial Intelligence.Google ScholarCross Ref
- Daniel Zügner, Amir Akbarnejad, and Stephan Günnemann. 2018. Adversarial attacks on neural networks for graph data. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2847--2856.Google ScholarDigital Library
- Yuan Zuo, Guannan Liu, Hao Lin, Jia Guo, Xiaoqian Hu, and Junjie Wu. 2018. Embedding Temporal Network via Neighborhood Formation. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2857--2866.Google ScholarDigital Library
Index Terms
- Streaming Graph Neural Networks via Continual Learning
Recommendations
Streaming Graph Neural Networks with Generative Replay
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningTraining Graph Neural Networks (GNNs) incrementally is a particularly urgent problem, because real-world graph data usually arrives in a streaming fashion, and inefficiently updating of the models results in out-of-date embeddings, thus degrade its ...
Continual Learning with Neural Networks: A Review
CODS-COMAD '19: Proceedings of the ACM India Joint International Conference on Data Science and Management of DataContinual learning broadly refers to the algorithms which aim to learn continuously over time across varying domains, tasks or data distributions. This is in contrast to algorithms restricted to learning a fixed number of tasks in a given domain, ...
Continual Learning on Dynamic Graphs via Parameter Isolation
SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information RetrievalMany real-world graph learning tasks require handling dynamic graphs where new nodes and edges emerge. Dynamic graph learning methods commonly suffer from the catastrophic forgetting problem, where knowledge learned for previous graphs is overwritten by ...
Comments