Approach For Influence Maximization Research Articles

A Dominance Approach for Influence Maximization with Incomplete Information in Social Network

Influence maximization plays an important role in social network analysis and has been extensively explored due to its emergence in a great deal of applications. However, a vast majority of researchers have only considered the influence of one factor on the spread of information among individuals. In addition, this factor which is mainly the influence probability, has been considered to be fixed which is estimated based on the number of neighbors of each individual. While, in reality, we do not have complete information about this probability and it is not a fixed value. Moreover, in the spread of information, other factors including trust, are also involved, which cannot be easily combined due to their different nature. In this paper, a dominance approach to influence maximization is studied under the condition, in which, complete information about influence of users on each other is not available and users infect each other based on an unknown influence probability. Furthermore, in order to make the proposed model closer to reality, trust factor is also considered as an independent factor. The proposed method is compared to several state-of-the-art influence maximization algorithms and attained results on several synthetic and real social network datasets verify effectiveness of the proposed method compared to previous methods in the context of influence maximization.

Deep graph representation learning for influence maximization with accelerated inference

Selecting a set of initial users from a social network in order to maximize the envisaged number of influenced users is known as influence maximization (IM). Researchers have achieved significant advancements in the theoretical design and performance gain of several classical approaches, but these advances are almost reaching their pinnacle. Learning-based IM approaches have emerged recently with a higher generalization to unknown graphs than conventional methods. The development of learning-based IM methods is still constrained by a number of fundamental hardships, including (1) solving the objective function efficiently, (2) struggling to characterize the diverse underlying diffusion patterns, and (3) adapting the solution to different node-centrality-constrained IM variants. To address the aforementioned issues, we design a novel framework DeepIM for generatively characterizing the latent representation of seed sets, as well as learning the diversified information diffusion pattern in a data-driven and end-to-end way. Subsequently, we design a novel objective function to infer optimal seed sets under flexible node-centrality-based budget constraints. Extensive analyses are conducted over both synthetic and real-world datasets to demonstrate the overall performance of DeepIM.

Influence Maximization in Dynamic Networks Using Reinforcement Learning

Influence maximization (IM) has been widely studied in recent decades, aiming to maximize the spread of influence over networks. Despite many works for static networks, fewer research studies have been dedicated to the IM problem for dynamic networks, which creates many challenges. An IM method for such an environment, should consider its dynamics and perform well under different network structures. To fulfill this objective, more computations are required. Hence, an IM approach should be efficient enough to be applicable for the ever-changing structure of a network. In this research, an IM method for dynamic networks has been proposed which uses a deep Q-learning (DQL) approach. To learn dynamic features from the network and retain previously learned information, incremental and transfer learning methods have been applied. Experiments substantiate the good performance of the DQL methods and their superiority over compared methods on larger sizes of tested synthetic and real-world networks. These experiments illustrate better performance for incremental and transfer learning methods on real-world networks.

PHEE: Identifying influential nodes in social networks with a phased evaluation-enhanced search

How to identify a small fraction of users with the best capacity to influence other users is central to the research of social network analysis. This problem is termed influence maximization (IM) and is known for its extensive applications. IM can be formulated as a combinatorial optimization problem, which has been shown to be NP-hard under some diffusion models. Therefore, seeking for high-accuracy IM algorithms with acceptable running time has attracted much attention in literature. However, most of existing IM algorithms only adopt a uniform mechanism in the whole solution search process, which lacks of flexible response when the algorithms trap in local optimum. This paper proposes a phased evaluation-enhanced (PHEE) approach for IM, which utilizes two distinct strategies to search the optimal solutions: The first one is a random range division-based evolutionary algorithm for improving solution quality; the second is a fast convergence strategy for searching an optimal solution. Two PHEE-based algorithms, MDD-PHEE and GCI-PHEE, are generated and are evaluated on 10 real-world social networks of different sizes and types. Experimental results demonstrate the effectiveness of PHEE; in particular, MDD-PHEE obtains the best influence spread on all networks compared with the state-of-the-art algorithms, and has a better performance than the time-consuming algorithm CELF on four datasets.

Influence Maximization in social networks using discretized Harris’ Hawks Optimization algorithm

Influence Maximization (IM) is the task of determining k optimal influential nodes in a social network to maximize the influence spread using a propagation model. IM is a prominent problem for viral marketing and helps significantly in social media advertising. Previous Greedy and Reverse Influence Sampling-based IM approaches are ineffective in real-world social networks due to their significant computational cost and execution time. Further, even heuristic approaches applied to IM generally yield minimal performance gain relative to the decreased time complexity. This presents a challenge in developing cost-effective algorithms with low execution time that can handle diverse social networks. In this paper, we propose the discretization of the nature-inspired Harris’ Hawks Optimization meta-heuristic algorithm using community structures for optimal selection of seed nodes for influence spread. In addition to Harris’ Hawks’ intelligence, we employ a neighbor scout strategy algorithm to avoid blindness and enhance the searching ability of the hawks. Further, we use a candidate nodes-based random population initialization approach, and these candidate nodes aid in accelerating the convergence process for the entire populace, reducing the total computational cost. We evaluate the efficacy of our proposed DHHO approach on eight social networks using the Independent Cascade model for information diffusion. We observe that DHHO is comparable or better than competing meta-heuristic approaches for Influence Maximization across five metrics, and performs noticeably better than competing heuristic approaches.

Influence- and Interest-Based Worker Recruitment in Crowdsourcing Using Online Social Networks

Workers recruitment remains a significant issue in Mobile Crowdsourcing (MCS), where the aim is to recruit a group of workers that maximizes the expected Quality of Service (QoS). Current recruitment systems assume that a pre-defined pool of workers is available. However, this assumption is not always true, especially in cold-start situations, where a new MCS task has just been released. Additionally, studies show that up to 96% of the available candidates are usually not willing to perform the assigned tasks. To tackle these issues, recent works use Online Social Networks (OSNs) and Influence Maximization (IM) to advertise about the desired MCS tasks through influencers, aiming to build larger pools. However, these works suffer from several limitations, such as 1) the lack of group-based selection methods when choosing influencers, 2) the lack of a well-defined worker recruitment process following IM, 3) and the non-dynamicity of the recruitment process, where the workers who refuse to perform the task are not substituted. In this paper, an Influence-and Interest-based Worker Recruitment System (IIWRS), using OSNs, is proposed. The proposed system has two main components: 1) an MCS-, group-, and interest-based IM approach, using a Genetic Algorithm, to select a set of influencers from the network to advertise about the MCS tasks, and 2) a dynamic worker recruitment process which considers the social attributes of workers, and is able to substitute those who do not accept to perform the assigned tasks. Empirical studies are performed using real-life datasets, while comparing IIWRS with existing benchmarks.

Robust Influence Maximization Under Both Aleatory and Epistemic Uncertainty

Uncertainty is ubiquitous in almost every real-life optimization problem, which must be effectively managed to get a robust outcome. This is also true for the Influence Maximization (IM) problem, which entails locating a set of influential users within a social network. However, most of the existing IM approaches have overlooked the uncertain factors in finding the optimal solution, which often leads to subpar performance in reality. A few recent studies have considered only the epistemic uncertainty (i.e., arises from the imprecise data), while ignoring completely the aleatory uncertainty (i.e., arises from natural or physical variability). In this article, we propose a formulation and a novel algorithm for the Robust Influence Maximization (RIM) problem under both types of uncertainties. First, we develop a robust influence spread function under aleatory uncertainty that, in contrast to the existing IM theory, is no longer monotone and submodular. Thereafter, we expand our RIM formulation to incorporate epistemic uncertainty aiming to maximize the robust ratio between the selected worst-case solution and the best-case optimal solution, adopting a conservative approach. Furthermore, using a chance-constraint-based method, we investigated feasibility robustness by accounting for the uncertainties related to constraint functions. Finally, an Evolutionary Algorithm (named EA-RIM) is designed to solve the proposed formulation of the RIM problem. Experimental evaluation results on four empirical datasets show that our proposed formulation and algorithm are more effective in dealing with uncertainties and finding an optimal solution for the RIM problem.

ABEM: An adaptive agent-based evolutionary approach for influence maximization in dynamic social networks

Influence maximization is recognized as a crucial optimization problem, which aims to identify a limited set of influencers to maximize the coverage of influence dissemination in social networks. However, real-world social networks are usually dynamic and large-scale, which leads to difficulty in capturing real-time user and diffusion features to effectively and accurately select the key influencers. In this paper, we propose an adaptive agent-based evolutionary approach to address this challenging issue with agent-based modeling and genetic algorithm. This novel approach identifies the users’ influence capability in a distributed manner and optimizes the influencer set selection in a dynamic environment. An adaptive solution optimizer is proposed as one of the key components, driving the evolutionary process and adapting the candidate solutions dynamically. The proposed approach is also applicable to large-scale networks due to its distributed framework. Evaluation of our approach is performed by using both synthetic networks and real-world datasets. Experimental results demonstrate that the proposed approach outperforms state-of-the-art seeding algorithms in terms of maximizing influence.

Hybrid Approach for Detecting Propagandistic Community and Core Node on Social Networks

People share their views and daily life experiences on social networks and form a network structure. The information shared on social networks can be unreliable, and detecting such kinds of information may reduce mass panic. Propaganda is a kind of biased or unreliable information that can mislead or intend to promote a political cause. The disseminators involved in spreading such information create a sophisticated network structure. Detecting such communities can lead to a safe and reliable network for the users. In this paper, a Boundary-based Community Detection Approach (BCDA) has been proposed to identify the core nodes in a propagandistic community that detects propagandistic communities from social networks with the help of interior and boundary nodes. The approach consists of two phases, one is to detect the community, and the other is to detect the core member. The approach mines nodes from the boundary as well as from the interior of the community structure. The leader Ranker algorithm is used for mining candidate nodes within the boundary, and the Constraint coefficient is used for mining nodes within the boundary. A novel dataset is generated from Twitter. About six propagandistic communities are detected. The core members of the propagandistic community are a combination of a few nodes. The experiments are conducted on a newly collected Twitter dataset consisting of 16 attributes. From the experimental results, it is clear that the proposed model outperformed other related approaches, including Greedy Approach, Improved Community-based 316 Robust Influence Maximization (ICRIM), Community Based Influence Maximization Approach (CBIMA), etc. It was also observed from the experiments that most of the propagandistic information is being shared during trending events around the globe, for example, at times of the COVID-19 pandemic.

Influence maximization through exploring structural information

Influence maximization (IM) is a widely investigated issue in the study of social networks because of its potential commercial and social value. The purpose of IM is to identify a group of influential nodes that will spread information to other nodes in a network while simultaneously maximizing the number of nodes that are ultimately influenced. Traditional IM methods have different limitations, such as limited scalability to address large-scale networks and the neglect of community structural information. Here, we propose a novel influence maximization approach, i.e., the layered gravity bridge algorithm (LGB), to address the IM problem, which emphasizes the local structural information of networks and combines community detection algorithms with an improved gravity model. With the proposed LGB, a community detection method is used to derive the communities, and then the bridge nodes are found, which can be regarded as possible candidate seeds. Later, communities are merged into larger communities according to our proposed algorithm, and new bridge nodes are determined. Finally, all candidate seed nodes are sorted through an improved gravity model to determine the final seed nodes. The algorithm fully explores the network structural information provided by the communities, thereby making it superior to the current algorithms in terms of the number of ultimately infected nodes. Furthermore, our proposed algorithm possesses the potential to alleviate the influence overlap effect of seed nodes. To verify the effect of our approach, the classical SIR model is adopted to propagate information with the selected seed nodes, while experiments are performed on several practical datasets. As indicated by the obtained results, the performance of our proposed algorithm outperforms existing ones.

BatchedGreedy: A batch processing approach for influence maximization with candidate constraint

BatchedGreedy: A batch processing approach for influence maximization with candidate constraint

A two-stage VIKOR assisted multi-operator differential evolution approach for Influence Maximization in social networks

The impact of online social networking on daily life is extending beyond personal boundaries, becoming a tool for financial activities and even public well-being. Interactions among users and items, as nodes of such networks, and flows of information among them play a critical role in this regard. Identifying a small subset of such nodes with maximum spreading power that facilitates this process has attracted a lot of attention. The existing solution approaches to this NP-hard combinatorial optimization problem, known as the Influence Maximization (IM) problem, mainly suffer either from poor solution quality or large computational time. This study addresses these issues by proposing a two-stage optimization framework. First, to reduce the computation complexity, a multi-criteria decision making (MCDM) approach is employed to prune insignificant nodes from the candidate nodes. Second, to optimize the solutions, a modified differential evolution (DE) algorithm equipped with multiple search operators is proposed. The proposed algorithm uses the Expected Diffusion Value (EDV) in place of traditional time-consuming simulations to evaluate the fitness of a candidate solution. We proved that EDV is a monotone and submodular function, and showed that it can effectively and efficiently be integrated into a greedy-based algorithmic framework. We also provided the theoretical analysis and evaluated the performance of this proposed algorithm experimentally using two synthetic and eight diverse real-life networks. The experimental results show that our proposed algorithm achieves a better trade-off between solution quality and running time compared to the existing baseline algorithms.

Hashtags Influence Maximization: Choosing the most Influential Hashtags on Instagram

This study aims to find influential hashtags using Influence Maximization (IM). The IM approach was implemented using hashtags network collected from Instagram. This study can help business or ordinary users to choose the most engaging hashtags for posting, as opposed to selecting influencers, which was widely studied using the IM approach. The network was build based on the hashtags co-appearance frequency. Three IM algorithms, i.e. SSA, DSSA, and IMM, were simulated under the IC and LT models. The algorithms were compared against TopUsage, which is the top hashtags based on the usage count. The IM algorithms have a similar performance with TopUsage in influence spread, which shows that IM can adapt to the hashtags network. However, the IM algorithms produced better hashtags based on the UER (unique engagement rate) metric. The best UER performance was shown by DSSA under the LT model, where it outperformed TopUsage by 17.23%. In the hashtags categorization scenario, DSSA-LT outperformed the UER of TopUsage by up to 6.87%. This categorization is more useful in a practical scenario, to find only relevant hashtags for posting. The hashtags generated by DSSA-LT are about 30-35% different from TopUsage.

A novel meta‐heuristic approach for influence maximization in social networks

AbstractInfluence maximization in a social network focuses on the task of extracting a small set of nodes from a network which can maximize the propagation in a cascade model. Though greedy methods produce good solutions to the aforementioned problem, their high computational complexity is a major drawback. Centrality‐based heuristic methods often fail to overcome local optima, thereby producing sub‐optimal results. To this end, in this article, a framework has been presented which involves community detection in a social network and the utilization of the Shuffled Frog Leaping algorithm, in maximizing the two‐hop spread of influence under the independent cascade model. Local search strategies like the Late acceptance based hill climbing have been employed to improve the solution further. Experiments performed on three real‐world datasets have shown that our method performs markedly well with respect to the comparing algorithms.

Influence maximization in social graphs based on community structure and node coverage gain

Influence maximization is an optimization problem in the area of social graph analysis, which asks to choose a subset of k individuals to maximize the number of influenced nodes at the end of the diffusion process. As individuals within a community have frequent contact and are more likely to influence each other, community-based influence maximization has attracted considerable attentions. However, this kind of works ignores the role of overlapping nodes in community structure, resulting in performance degradation in seeds selection. In addition, many existing community-based algorithms identify the final seeds only from the selected important communities, or they need to leverage the weights between local spread and global spread of a node. It is difficult to set suitable scales for important communities or to determine the weights for different spread. In this paper, we propose a novel influence maximization approach based on overlapping community structure and node coverage gain. Firstly, social graphs are partitioned into different overlapping communities by the algorithm of node location analysis in topological potential field. Secondly, a node coverage gain sensitive centrality measure is put up to evaluate the influence of each node locally within its belonging communities, which avoids the problem of local spread and global spread. Finally, seed nodes are directly selected by combining the detected community structure with the pre-designed strategy, without important communities identification. The comprehensive experiments under both the Uniform Independent Cascade model and the Weighted Independent Cascade model demonstrate that our proposed approach can achieve competitive influence spread, outperforming state-of-the-art works. Furthermore, our proposed approach exhibits stable performance on graphs with different scales and various structural characteristics.

LIDDE: A differential evolution algorithm based on local-influence-descending search strategy for influence maximization in social networks

Influence maximization aims to select k seed nodes from social networks so that the expected number of nodes activated by the seed nodes can be maximized. With the development and popularity of Internet technology, the influence maximization has become a vital problem, especially for viral marketing. However, most existing algorithms utilize the greedy strategy to select seed nodes, which usually leads themselves into local optimal solution. Most other algorithms that not based on the greedy strategy usually have low efficiency. Therefore, a Local-Influence-Descending search strategy is proposed, which can obtain a node set in which each node has relatively large influence. Afterwards, based on this strategy, a new approach for influence maximization is proposed to solve these problems, called Local-Influence-Descending Differential Evolution (LIDDE). It can improve the accuracy as well as the computation efficiency of influence maximization algorithms based on swarm intelligence. Experimental results on six real-world social networks demonstrate that the proposed algorithm outperforms all comparison algorithms in terms of accuracy and all algorithms based on swarm intelligence in terms of efficiency.

An MCDM integrated adaptive simulated annealing approach for influence maximization in social networks

The Influence Maximization (IM) problem aims to identify a small subset of nodes that have the most influence spread in a network. Although it is an NP-hard problem, the continuous increasing size of the social networks leads to a substantially higher computational complexity, and therefore, has motivated numerous researchers to explore better approaches. This paper proposes a multi-criteria decision making (MCDM) based meta-heuristic approach to solve the IM problem in social networks. An MCDM approach is utilized to select candidate nodes by eliminating less influential ones at the preliminary phase which decreases the computation cost. Thereafter, to find the optimal solution, a modified version of Simulated Annealing (SA) with an enhanced search strategy is proposed. The performance of this proposed approach is tested and verified by solving the IM problem on eight real-life social networks of different sizes and types and comparing the results with six benchmark algorithms. The experimental results indicate that the proposed algorithm has a better trade-off between the solution quality and computational run time than the other algorithms.

An efficient path-based approach for influence maximization in social networks

It is no secret that the word-of-mouth has very powerful effect on the social interconnections, but the question is “which factors influence the word-of-mouth effectiveness?” The answer hinges on a small set of nodes if activated, would spread information all over the network. This is a major issue in the social network analysis, known as the influence maximization, through which the influence spreading through a small set of seed nodes is maximized. Finding this highly influential node set has still remained challenging due to the non-deterministic polynomial-time (NP)-hard nature of the influence maximization problem and the significant increase in the size of social networks. Thus, in this paper, an efficient path-based algorithm was proposed to address this problem from two complementary perspectives adapting the proposed algorithm in the large-scale networks. One perspective is approximating the influence spread efficiently using two features of the nodes: the degrees and the independent influence path. The second perspective is pruning out the uninfluential nodes and reducing the computation volume in approximating the influence spread using a practical preprocessing heuristic method. Extensive empirical experiments were conducted to evaluate the performance of the proposed algorithm in the seven real-world networks and the results were compared with a plenty of the state-of-the-art algorithms. The results revealed that the proposed algorithm outperforms its counterparts, by offering an outstanding trade-off between the quality and efficiency.

Influential node identification in a constrained greedy way

Influence maximization aims to identify a set of influential nodes as seeds to initiate the propagation of influence so that the influence can be spread most widely. It plays critical roles in the areas such as rumor controlling, viral marketing and so on. Greedy algorithms have been exploited to identify seeds. They have been proved to provide the results approximating the optimum. However, non-neglectable iterative calculations and influence overlap between seeds degrade the performance and the efficiency of those algorithms. To alleviate the performance and efficiency degradation, we propose an influence maximization approach based on the property of submodularity. The approach selects seeds according to the influence propagated in a constrained greedy way to alleviate the performance degradation caused by non-neglectable iterative calculations. It performs rigorous overlap cost checks on the nodes which could be taken as seeds to relieve the efficiency degradation caused by the influence overlap. The experiments verify the performance and the efficiency of the approach.

Large-scale influence maximization via maximal covering location

Influence maximization aims at identifying a limited set of key individuals in a (social) network which spreads information based on some propagation model and maximizes the number of individuals reached. We show that influence maximization based on the probabilistic independent cascade model can be modeled as a stochastic maximal covering location problem. A reformulation based on Benders decomposition is proposed and a relation between obtained Benders optimality cuts and submodular cuts for correspondingly defined subsets is established. We introduce preprocessing tests, which allow us to remove variables from the model and develop efficient algorithms for the separation of Benders cuts. Both aspects are shown to be crucial ingredients of the developed branch-and-cut algorithm since real-life social network instances may be very large. In a computational study, the considered variants of this branch-and-cut algorithm outperform the state-of-the-art approach for influence maximization by orders of magnitude.