Robust Influence Maximization Under Both Aleatory and Epistemic Uncertainty (original) (raw)

A robust optimization model for influence maximization in social networks with heterogeneous nodes

Computational Social Networks

Influence maximization is the problem of trying to maximize the number of influenced nodes by selecting optimal seed nodes, given that influencing these nodes is costly. Due to the probabilistic nature of the problem, existing approaches deal with the concept of the expected number of nodes. In the current research, a scenario-based robust optimization approach is taken to finding the most influential nodes. The proposed robust optimization model maximizes the number of infected nodes in the last step of diffusion while minimizing the number of seed nodes. Nodes, however, are treated as heterogeneous with regard to their propensity to pass messages along; or as having varying activation thresholds. Experiments are performed on a real text-messaging social network. The model developed here significantly outperforms some of the well-known existing heuristic approaches which are proposed in previous works.

Influence Maximization Revisited: The State of the Art and the Gaps that Remain

2019

The steady growth of graph data from social networks has resulted in wide-spread research on the influence maximization (IM) problem. This results in extension of the state-of-the-art almost every year. With the recent explosion in the application of IM in solving real-world problems, it is no longer a theoretical exercise. Today, IM is used in a plethora of real-world scenarios, with OnePlus1 series of mobile phones, Hokey Pokey2 ice-creams, and galleri5 influencer marketplace3 being the most prominent industrial use-cases. Given this scenario, navigating the maze of IM techniques to get an in-depth understanding of their utilities is of prime importance. In this tutorial, we address this paramount issue and solve the dilemma of “Which IM technique to use and under What scenarios”? “What does it really mean to claim to be the state-of-the-art”? This tutorial builds upon our benchmarking study [1], and will provide a concise and intuitive overview of the most important IM techniques...

Leveraging Uncertainty Analysis of Data to Evaluate User Influence Algorithms of Social Networks

2018

Identifying of highly influential users in social networks is critical in various practices, such as advertisement, information recommendation, and surveillance of public opinion. According to recent studies, different existing user influence algorithms generally produce different results. There are no effective metrics to evaluate the representation abilities and the performance of these algorithms for the same dataset. Therefore, the results of these algorithms cannot be accurately evaluated and their limits cannot be effectively observered. In this paper, we propose an uncertainty-based Kalman filter method for predicting user influence optimal results. Simultaneously, we develop a novel evaluation metric for improving maximum correntropy and normalized discounted cumulative gain (NDCG) criterion to measure the effectiveness of user influence and the level of uncertainty fluctuation intervals of these algorithms. Experimental results validate the effectiveness of the proposed alg...

A numerical evaluation of the accuracy of influence maximization algorithms

Social Network Analysis and Mining

We develop an algorithm to compute exact solutions to the influence maximization problem using concepts from reverse influence sampling (RIS). We implement the algorithm using GPU resources to evaluate the empirical accuracy of theoretically-guaranteed greedy and RIS approximate solutions. We find that the approximations yield solutions that are remarkably close to optimal-usually achieving greater than 99% of the optimal influence spread. These results are consistent across a wide range of network structures.

Influence maximization of informed agents in social networks

Control of collective behavior is one of the most desirable goals in many applications related to social networks analysis and mining. In this work we propose a simple yet effective algorithm to control opinion formation in complex networks. We aim at finding the best spreaders whose connection to a reasonable number of informed agents results in the best performance. We consider an extended version of the bounded confidence model in which the uncertainty of each agent is adaptively controlled by the network. A number of informed agents with the desired opinion value is added to the network and create links with other agents such that large portion of the network follows their opinions. We propose to connect the informed agents to nodes with small in-degrees and high out-degree that are connected to high in-degree nodes. Our experimental results on both model and real social networks show superior performance of the proposed method over the stateof-the-art heuristic methods in the facet of opinion formation models.

Holistic Influence Maximization

Proceedings of the 2016 International Conference on Management of Data - SIGMOD '16, 2016

The steady growth of graph data from social networks has resulted in widespread research in finding solutions to the influence maximization problem. In this paper, we propose a holistic solution to the influence maximization (IM) problem. (1) We introduce an opinion-cum-interaction (OI) model that closely mirrors the real-world scenarios. Under the OI model, we introduce a novel problem of Maximizing the Effective Opinion (MEO) of influenced users. We prove that the MEO problem is NP-hard and cannot be approximated within a constant ratio unless P=NP. (2) We propose a heuristic algorithm OSIM to efficiently solve the MEO problem. To better explain the OSIM heuristic, we first introduce EaSyIMthe opinion-oblivious version of OSIM, a scalable algorithm capable of running within practical compute times on commodity hardware. In addition to serving as a fundamental building block for OSIM, EaSyIM is capable of addressing the scalability aspectmemory consumption and running time, of the IM problem as well. Empirically, our algorithms are capable of maintaining the deviation in the spread always within 5% of the best known methods in the literature. In addition, our experiments show that both OSIM and EaSyIM are effective, efficient, scalable and significantly enhance the ability to analyze real datasets.

A two-stage stochastic programming approach for influence maximization in social networks

Computational Optimization and Applications, 2017

We consider stochastic influence maximization problems arising in social networks. In contrast to existing studies that involve greedy approximation algorithms with a 63% performance guarantee, our work focuses on solving the problem optimally. To this end, we introduce a new class of problems that we refer to as two-stage stochastic submodular optimization models. We propose a delayed constraint generation algorithm to find the optimal solution to this class of problems with a finite number of samples. The influence maximization problems of interest are special cases of this general problem class. We show that the submodularity of the influence function can be exploited to develop strong optimality cuts that are more effective than the standard optimality cuts available in the literature. Finally, we report our computational experiments with large-scale real-world datasets for two fundamental influence maximization problems, independent cascade and linear threshold, and show that our proposed algorithm outperforms the greedy algorithm.

Multi-Objective Influence Maximization

2021

Influence Maximization (IM) is the problem of finding a set of influential users in a social network, so that their aggregated influence is maximized. The classic IM problem focuses on the single objective of maximizing the overall number of influenced users. While this serves the goal of reaching a large audience, users often have multiple specific sub-populations they would like to reach within a single campaign, and consequently multiple influence maximization objectives. As we show, maximizing the influence over one group may come at the cost of significantly reducing the influence over the others. To address this, we propose IM-Balanced, a system that allows users to explicitly declare the desired balance between the objectives. IM-Balanced employs a refined notion of the classic IM problem, called MultiObjective IM, where all objectives except one are turned into constraints, and the remaining objective is optimized subject to these constraints. We prove Multi-Objective IM to ...

SIMPATH: An Efficient Algorithm for Influence Maximization under the Linear Threshold Model

2011 IEEE 11th International Conference on Data Mining, 2011

There is significant current interest in the problem of influence maximization: given a directed social network with influence weights on edges and a number k, find k seed nodes such that activating them leads to the maximum expected number of activated nodes, according to a propagation model. Kempe et al.

A Community-Aware Framework for Social Influence Maximization

arXiv (Cornell University), 2022

We consider the problem of Influence Maximization (IM), the task of selecting k seed nodes in a social network such that the expected number of nodes influenced is maximized. We propose a community-aware divide-and-conquer framework that involves (i) learning the inherent community structure of the social network, (ii) generating candidate solutions by solving the influence maximization problem for each community, and (iii) selecting the final set of seed nodes using a novel progressive budgeting scheme. Our experiments on real-world social networks show that the proposed framework outperforms the standard methods in terms of run-time and the heuristic methods in terms of influence. We also study the effect of the community structure on the performance of the proposed framework. Our experiments show that the community structures with higher modularity lead the proposed framework to perform better in terms of run-time and influence.