MIM-Reasoner: Learning with Theoretical Guarantees for Multiplex Influence Maximization

Nguyen Hoang Khoi Do, Tanmoy Chowdhury, Chen Ling, Liang Zhao, My T. Thai
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:2296-2304, 2024.

Abstract

Multiplex influence maximization (MIM) asks us to identify a set of seed users such as to maximize the expected number of influenced users in a multiplex network. MIM has been one of central research topics, especially in nowadays social networking landscape where users participate in multiple online social networks (OSNs) and their influences can propagate among several OSNs simultaneously. Although there exist a couple combinatorial algorithms to MIM, learning-based solutions have been desired due to its generalization ability to heterogeneous networks and their diversified propagation characteristics. In this paper, we introduce MIM-Reasoner, coupling reinforcement learning with probabilistic graphical model, which effectively captures the complex propagation process within and between layers of a given multiplex network, thereby tackling the most challenging problem in MIM. We establish a theoretical guarantee for MIM-Reasoner as well as conduct extensive analyses on both synthetic and real-world datasets to validate our MIM-Reasoner’s performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v238-hoang-khoi-do24a, title = {MIM-Reasoner: Learning with Theoretical Guarantees for Multiplex Influence Maximization}, author = {Hoang Khoi Do, Nguyen and Chowdhury, Tanmoy and Ling, Chen and Zhao, Liang and T. Thai, My}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics}, pages = {2296--2304}, year = {2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, month = {02--04 May}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v238/hoang-khoi-do24a/hoang-khoi-do24a.pdf}, url = {https://proceedings.mlr.press/v238/hoang-khoi-do24a.html}, abstract = {Multiplex influence maximization (MIM) asks us to identify a set of seed users such as to maximize the expected number of influenced users in a multiplex network. MIM has been one of central research topics, especially in nowadays social networking landscape where users participate in multiple online social networks (OSNs) and their influences can propagate among several OSNs simultaneously. Although there exist a couple combinatorial algorithms to MIM, learning-based solutions have been desired due to its generalization ability to heterogeneous networks and their diversified propagation characteristics. In this paper, we introduce MIM-Reasoner, coupling reinforcement learning with probabilistic graphical model, which effectively captures the complex propagation process within and between layers of a given multiplex network, thereby tackling the most challenging problem in MIM. We establish a theoretical guarantee for MIM-Reasoner as well as conduct extensive analyses on both synthetic and real-world datasets to validate our MIM-Reasoner’s performance.} }
Endnote
%0 Conference Paper %T MIM-Reasoner: Learning with Theoretical Guarantees for Multiplex Influence Maximization %A Nguyen Hoang Khoi Do %A Tanmoy Chowdhury %A Chen Ling %A Liang Zhao %A My T. Thai %B Proceedings of The 27th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2024 %E Sanjoy Dasgupta %E Stephan Mandt %E Yingzhen Li %F pmlr-v238-hoang-khoi-do24a %I PMLR %P 2296--2304 %U https://proceedings.mlr.press/v238/hoang-khoi-do24a.html %V 238 %X Multiplex influence maximization (MIM) asks us to identify a set of seed users such as to maximize the expected number of influenced users in a multiplex network. MIM has been one of central research topics, especially in nowadays social networking landscape where users participate in multiple online social networks (OSNs) and their influences can propagate among several OSNs simultaneously. Although there exist a couple combinatorial algorithms to MIM, learning-based solutions have been desired due to its generalization ability to heterogeneous networks and their diversified propagation characteristics. In this paper, we introduce MIM-Reasoner, coupling reinforcement learning with probabilistic graphical model, which effectively captures the complex propagation process within and between layers of a given multiplex network, thereby tackling the most challenging problem in MIM. We establish a theoretical guarantee for MIM-Reasoner as well as conduct extensive analyses on both synthetic and real-world datasets to validate our MIM-Reasoner’s performance.
APA
Hoang Khoi Do, N., Chowdhury, T., Ling, C., Zhao, L. & T. Thai, M.. (2024). MIM-Reasoner: Learning with Theoretical Guarantees for Multiplex Influence Maximization. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:2296-2304 Available from https://proceedings.mlr.press/v238/hoang-khoi-do24a.html.

Related Material