Robust cross-network node classification via constrained graph mutual information
Article
Yang, Shuiqiao, Cai, Borui, Cai, Taotao, Song, Xiangyu, Jiang, Jiaojiao, Li, Bing and Li, Jianxin. 2022. "Robust cross-network node classification via constrained graph mutual information." Knowledge-Based Systems. 257. https://doi.org/10.1016/j.knosys.2022.109852
| Article Title | Robust cross-network node classification via constrained graph mutual information |
|---|---|
| ERA Journal ID | 18062 |
| Article Category | Article |
| Authors | Yang, Shuiqiao, Cai, Borui, Cai, Taotao, Song, Xiangyu, Jiang, Jiaojiao, Li, Bing and Li, Jianxin |
| Journal Title | Knowledge-Based Systems |
| Journal Citation | 257 |
| Article Number | 109852 |
| Number of Pages | 10 |
| Year | 2022 |
| Publisher | Elsevier |
| Place of Publication | Netherlands |
| ISSN | 0950-7051 |
| 1872-7409 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1016/j.knosys.2022.109852 |
| Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S0950705122009455 |
| Abstract | The recent methods for cross-network node classification mainly exploit graph neural networks (GNNs) as feature extractor to learn expressive graph representations across the source and target graphs. However, GNNs are vulnerable to noisy factors, such as adversarial attacks or perturbations on the node features or graph structure, which can cause a significant negative impact on their learning performance. To this end, we propose a robust graph domain adaptive learning framework RGDAL which exploits an information-theoretic principle to filter the noisy factors for cross-network node classification. Specifically, RGDAL utilizes graph convolutional network (GCN) with constrained graph mutual information and an adversarial learning component to learn noise-resistant and domain-invariant graph representations. To overcome the difficulties of estimating the mutual information for the non independent and identically distributed (non-i.i.d.) graph structured data, we design a dynamic neighborhood sampling strategy that can discretize the graph and incorporate the graph structural information for mutual information estimation. Experimental results on two real-world graph datasets demonstrate that RGDAL shows better robustness for cross-network node classification compared with the SOTA graph adaptive learning methods. |
| Keywords | Graph domain adaptive learning; Node classification; Graph neural networks; Mutual information |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 4602. Artificial intelligence |
| Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
| Byline Affiliations | University of New South Wales |
| Deakin University | |
| Macquarie University | |
| Agency for Science Technology And Research, Singapore |
Permalink -
https://research.usq.edu.au/item/z6039/robust-cross-network-node-classification-via-constrained-graph-mutual-information
19
total views0
total downloads2
views this month0
downloads this month
Export as
Related outputs
FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning
Shaik, Thanveer, Tao, Xiaohui, Li, Lin, Xie, Haoran, Cai, Taotao, Zhu, Xiaofeng and Li, Qing. 2024. "FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning ." IEEE Transactions on Knowledge and Data Engineering. https://doi.org/10.1109/TKDE.2024.3382726Reconnecting the Estranged Relationships: Optimizing the Influence Propagation in Evolving Networks
Cai, Taotao, Lei, Qi, Sheng, Quan Z., Cui, Ningning, Yang, Shuiqiao, Yang, Jian, Zhang, Wei Emma and Mahmood, Adnan. 2024. "Reconnecting the Estranged Relationships: Optimizing the Influence Propagation in Evolving Networks." IEEE Transactions on Knowledge and Data Engineering. 36 (5), pp. 2151-2165. https://doi.org/10.1109/TKDE.2023.3316268Dynamic Correlation Adjacency Matrix Based Graph Neural Network for Traffic Flow Prediction
Gu, Junhua, Jia, Zhihao, Cai, Taotao, Song, Xiangyu and Mahmood, Adnan. 2023. "Dynamic Correlation Adjacency Matrix Based Graph Neural Network for Traffic Flow Prediction." Sensors. 23 (6). https://doi.org/10.3390/s23062897Top-k socio-spatial co-engaged location selection for social users
Hasan Haldar, Nur Al, Li, Jianxin, Ali, Mohammed Eunus, Cai, Taotao, Chen, Yunliang, Sellis, Timos and Reynolds, Mark. 2023. "Top-k socio-spatial co-engaged location selection for social users." IEEE Transactions on Knowledge and Data Engineering. 35 (5), pp. 5325-5340. https://doi.org/10.1109/TKDE.2022.3151095Towards Multi-User, Secure, and Verifiable kNN Query in Cloud Database
Cui, Ningning, Qian, Kang, Cai, Taotao, Li, Jianxin, Yang, Xiaochun, Cui, Jie and Zhong, Hong. 2023. "Towards Multi-User, Secure, and Verifiable kNN Query in Cloud Database." IEEE Transactions on Knowledge and Data Engineering. 35 (9), pp. 9333-9349. https://doi.org/10.1109/TKDE.2023.3237879Incremental graph computation: Anchored Vertex Tracking in Dynamic Social Networks
Cai, Taotao, Yang, Shuiqiao, Li, Jianxin, Sheng, Quan Z., Yang, Jian, Wang, Xin, Zhang, Wei Emma and Gao, Longxiang. 2023. "Incremental graph computation: Anchored Vertex Tracking in Dynamic Social Networks." IEEE Transactions on Knowledge and Data Engineering. 35 (7), pp. 7030-7044. https://doi.org/10.1109/TKDE.2022.3199494New achievements on daily reference evapotranspiration forecasting: Potential assessment of multivariate signal decomposition schemes
Ali, Mumtaz, Jamei, Mehdi, Prasad, Ramendra, Karbasi, Masoud, Xiang, Yong, Cai, Borui, Abdulla, Shahab, Farooque, Aitazaz Ahsan and Labban, Abdulhaleem H.. 2023. "New achievements on daily reference evapotranspiration forecasting: Potential assessment of multivariate signal decomposition schemes." Ecological Indicators. 155. https://doi.org/10.1016/j.ecolind.2023.111030Coupled online sequential extreme learning machine model with ant colony optimization algorithm for wheat yield prediction
Ali, Mumtaz, Deo, Ravinesh C., Xiang, Yong, Prasad, Ramendra, Li, Jianxin, Farooque, Aitazaz and Yaseen, Zaher Mundher. 2022. "Coupled online sequential extreme learning machine model with ant colony optimization algorithm for wheat yield prediction." Scientific Reports. 12 (1), pp. 1-23. https://doi.org/10.1038/s41598-022-09482-5A survey on deep learning based knowledge tracing
Song, Xiangyu, Li, Jianxin, Cai, Taotao, Yang, Shuiqiao, Yang, Tingting and Liu, Chengfei. 2022. "A survey on deep learning based knowledge tracing." Knowledge-Based Systems. 258. https://doi.org/10.1016/j.knosys.2022.110036Target-Aware Holistic Influence Maximization in Spatial Social Networks
Cai, Taotao, Li, Jianxin, Mian, Ajmal, Li, Rong-Hua, Sellis, Timos and Yu, Jeffrey Xu. 2022. "Target-Aware Holistic Influence Maximization in Spatial Social Networks ." IEEE Transactions on Knowledge and Data Engineering. 34 (4), pp. 1993-2007. https://doi.org/10.1109/TKDE.2020.3003047Self-supervised cross-iterative clustering for unlabeled plant disease images
Fang, Uno, Li, J., Lu, X., Gao, Longxiang, Ali, Mumtaz and Xiang, Yong. 2021. "Self-supervised cross-iterative clustering for unlabeled plant disease images." Neurocomputing. 456, pp. 36-48. https://doi.org/10.1016/j.neucom.2021.05.066Community-diversity Driven Influence Maximization on Social Networks
Li, Jianxin, Cai, Taotao, Ke, Deng, Wang, Xinjue, Sellis, Timos and Xia, Feng. 2020. "Community-diversity Driven Influence Maximization on Social Networks." Information Systems. 92. https://doi.org/10.1016/j.is.2020.101522Anchor vertex selection for enhanced reliability of traffic offloading service in edge-enabled mobile P2P social networks
Zhang, Hengda, Wang, Xiaofei, Fan, Hao, Cai, Taotao, Li, Jianxin, Li, Xiuhua and Leung, Victor C. M.. 2020. "Anchor vertex selection for enhanced reliability of traffic offloading service in edge-enabled mobile P2P social networks." Journal of Communications and Information Networks. 5 (2), pp. 217-224. https://doi.org/10.23919/JCIN.2020.9130437Anchored Vertex Exploration for Community Engagement in Social Networks
Cai, Taotao, Li, Jianxin, Hasan Haldar, Nur Al, Mian, Ajmal, Yearwood, John and Sellis, Timos. 2020. "Anchored Vertex Exploration for Community Engagement in Social Networks ." 2020 IEEE 36th International Conference on Data Engineering (ICDE). Dallas, United States 20 - 24 Apr 2020 United States. IEEE (Institute of Electrical and Electronics Engineers). https://doi.org/10.1109/ICDE48307.2020.00042Correlate Influential News Article Events to Stock Quote Movement
Mandalapu, Arun Chaitanya, Gunabalan, Saranya, Sadineni, Avinash, Cai, Taotao, Hasan, Nur Al Hasan and Li, Jianxin. 2019. "Correlate Influential News Article Events to Stock Quote Movement ." Li, Jianxin, Wang, Sen, Qin, Shaowen, Li, Xue and Wang, Shuliang (ed.) 15th International Conference on Advanced Data Mining and Applications. Dalian, China 21 - 23 Nov 2019 Switzerland. Springer. https://doi.org/10.1007/978-3-030-35231-8_24Holistic Influence Maximization for Targeted Advertisements in Spatial Social Networks
Li, Jianxin, Cai, Taotao, Mian, Ajmal, Li, Rong-Hua, Sellis, Timos and Yu, Jeffrey Xu. 2018. "Holistic Influence Maximization for Targeted Advertisements in Spatial Social Networks ." 2018 IEEE 34th International Conference on Data Engineering (ICDE). Paris, France 16 - 19 Apr 2018 United States. IEEE (Institute of Electrical and Electronics Engineers). https://doi.org/10.1109/ICDE.2018.00145Efficient Distance-based Representative Skyline Computation in 2D Space
Mao, Rui, Cai, Taotao, Li, Rong-Hua, Yu, Jeffery Xu and Li, Jianxin. 2017. "Efficient Distance-based Representative Skyline Computation in 2D Space." World Wide Web. 20 (4), pp. 621-638. https://doi.org/10.1007/s11280-016-0406-0Efficient Algorithms for Distance-Based Representative Skyline Computation in 2D Space
Cai, Taotao, Li, Rong-Hua, Yu, Jeffrey Xu, Mao, Rui and Cai, Yadi. 2015. "Efficient Algorithms for Distance-Based Representative Skyline Computation in 2D Space ." 17th Asia-Pacific Web Conference (APWeb2015). Guangzhou, China 18 - 20 Sep 2015 Switzerland . Springer. https://doi.org/10.1007/978-3-319-25255-1_10This item comprises data from the following sources: Web of Science