We are often dealing with decision-making tasks associated with models subject to environment uncertainties. Concerning an optimization problem with an unknown objective function, query-decision regression seeks to infer high-quality decisions for future queries by leveraging samples of query-decision pairs, without explicitly learning the unknown objective function. In this project, we develop algorithmic and learning foundations of query-decision regression, with potential applications in social network analysis, autonomous systems, and point cloud processing.
☸ NeurIPS 2021. Guangmo Tong. "USCO-Solver: Solving Undetermined Stochastic Combinatorial Optimization Problems." Advances in Neural Information Processing Systems 34 (2021): 1646-1659.
☸ NeurIPS 2020. Guangmo Tong. "StratLearner: learning a strategy for misinformation prevention in social networks." Advances in Neural Information Processing Systems 33 (2020): 15546-15555.
Dynamics of opinions, epidemics, and behaviors are fundamental phenomena. Accurately modeling the propagation process is a central issue in studying various dynamics. In this project, we develop modeling techniques using operational methods, point processes, and machine learning methods. In one branch, we leverage data-driven approaches aiming at capturing complex correlations between social cascades. In the other branch, we seek to design structure-preserving models that can enable effective predictive methods with provable performance guarantees.
☸ IJCAI 2022. Yifan Wang and Guangmo Tong. "Learnability of Competitive Threshold Models." the 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence, 2022
☸ ICME 2021. Chen Ling, Di Cui, Guangmo Tong, and Jianming Zhu. "On Forecasting Dynamics In Online Discussion Forums." IEEE International Conference on Multimedia and Expo, 2021.
☸ HyperText 2020. Chen Ling, Guangmo Tong, and Mozi Chen. "Nestpp: Modeling thread dynamics in online discussion forums." the 31st ACM conference on hypertext and social media, 2020.
Influence maximization is a classic social contagion management task that seeks to develop algorithms for maximizing the influence of social cascades. In this project, we study the influence maximization problem with the consideration of cascade competition as well as the case in which the seed nodes can be distributed into different rounds. Our research focuses on model development, algorithm design and analysis, and hardness analysis, using techniques of submodular optimization and graph sampling.
☸ TNSE 2021. Guangmo Tong, Ruiqi Wang, and Zheng Dong. "On Multi-Cascade Influence Maximization: Model, Hardness and Algorithmic Framework." IEEE Transactions on Network Science and Engineering, 2021.
☸ TCSS 2020. Guangmo Tong, Ruiqi Wang, Zheng Dong, and Xiang Li. "Time-constrained adaptive influence maximization." IEEE Transactions on Computational Social Systems, 2020.
☸ TETC 2020. Guangmo Tong, and Ruiqi Wang. "On adaptive influence maximization under general feedback models." IEEE Transactions on Emerging Topics in Computing, 2020.
The study of information containment focuses on developing methods for controlling the spread of negative information cascades, such as misinformation and violence-promoting messages. One important research problem is to develop seed placement strategies such that the positive cascade can effectively limit the spread of negative cascades. Our project has studied the information containment problem under a few operational diffusion models, delivering a collection of approximation algorithms and sampling methods with guaranteed performance.
☸ INFOCOM 2019. Guangmo Tong and Ding-Zhu Du. "Beyond uniform reverse sampling: A hybrid sampling technique for misinformation prevention." IEEE conference on computer communications, 2019.
☸ NeurIPS 2018. Guangmo Tong, Ding-Zhu Du, and Weili Wu. "On misinformation containment in online social networks." Advances in neural information processing systems 31, 2018.
☸ INFOCOM 2017. Guangmo Tong, Weili Wu, Ling Guo, Deying Li, Cong Liu, Bin Liu, and Ding-Zhu Du. "An efficient randomized algorithm for rumor blocking in online social networks." IEEE Conference on Computer Communications, 2017.
In collaboration with other research labs, our research aims to provide algorithmic and machine learning solutions to applications in various cyber-physical systems, including connected autonomous vehicles, wireless networks, real-time systems, and point cloud based sensing technologies.
☸ TIOT 2022. Zheng Dong, Yan Lu, Guangmo Tong, Yuanchao Shu, Shuai Wang, and Weisong Shi. "Watchdog: Real-time vehicle tracking on geo-distributed edge nodes." ACM Transactions on Internet of Things, 2022.
☸ IoT-J 2020. Mozi Chen, Kezhong Liu, Jie Ma, Xuming Zeng, Zheng Dong, Guangmo Tong, and Cong Liu. "MoLoc: Unsupervised fingerprint roaming for device-free indoor localization in a mobile ship environment." IEEE Internet of Things Journal, 2020.
☸ MetroCAD 2020. Zheng Dong, Weisong Shi, Guangmo Tong, and Kecheng Yang. "Collaborative autonomous driving: Vision and challenges." IEEE International Conference on Connected and Autonomous Driving, 2020.