Factorization Bandits for Online Influence Maximization

Wu, Qingyun; Li, Zhige; Wang, Huazheng; Chen, Wei; Wang, Honggang

doi:10.1145/3292500.3330874

Cited by 26 publications

(25 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…C2IM [28] focuses on influence communities' extraction in order to ease the connection to the influencers. Wu et al [37] propose the factorization of bandits' methods in order to predict influencers through iterations of reward strategies. However, it hardly scales in seed set sizes (generally 50) and, moreover, models are not designed to be time dependent and flexible.…”

Section: Algorithmsmentioning

confidence: 99%

Real-Time Influence Maximization in a RTB Setting

et al. 2020

View full text Add to dashboard Cite

To maximize the impact of an advertisement campaign on social networks, the real-time bidding (RTB) systems aim at targeting the most influential users of this network. Influence maximization (IM) is a solution that addresses this issue by maximizing the coverage of the network with top-k influencers who maximize the diffusion of information. Associated with online advertising strategies at Web scale, RTB is faced with complex ad placement decisions in real time to deal with a high-speed stream of online users. To tackle this issue, IM strategies should be modified in order to integrate RTB constraints. While most traditional IM methods deal with static sets of top influencers, they hardly address the dynamic influence targeting issue by integrating short time decision, no interchange and stream's incompleteness. This paper proposes a real-time influence maximization approach which takes influence maximization decisions within a real-time bidding environment. A deep analysis of influence scores of users over several social networks is presented as well a strategy to guarantee the impact of an IM strategy in order to define the budget of an ad campaign. Finally, we offer a thorough experimental process to compare static versus dynamic IM solutions wrt. influence scores.

show abstract

Section: Algorithmsmentioning

confidence: 99%

Real-Time Influence Maximization in a RTB Setting

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Incorporation of various factors have been studied, such as influence susceptibility [9], sentiment [10,11], freeloaders [12], targeted ads [13], and engagement [14,15]. There are also bandit-based IM algorithms [16,17] 1047 typically uses feedbacks from actual data. However, the benchmark methods were still based on influence spread, which makes the usefulness in real-world questionable.…”

Section: Introductionmentioning

confidence: 99%

Realistic influence maximization based on followers score and engagement grade on instagram

Purba

Yulia

2021

Bulletin EEI

View full text Add to dashboard Cite

In recent years, the emergence of social media influencers attracts the study of a realistic influence maximization (IM) technique. The theoretical performance of IM has become matured. However, it is not enough since IM has to be implemented in a social media environment. Realistic IM algorithms and diffusion models have been proposed, such as the addition of user factors or a learning agent. However, most studies still relied on the influence spread benchmark, which makes the usefulness questionable. This research is among the first IM study using Instagram data. In this study, two diffusion models are proposed, which are based on the original IC and LT models, with the addition of the engagement grade (EG) factor. An algorithm called IMFS (IM with followers score) is proposed to accommodate the new models as well as IC and LT. In addition, realistic benchmark methods are proposed, namely the average engagement of the activated users, and the overlapping between post likers and activated users. The result shows that the proposed models are 2-3x more realistic if compared to IC and LT.

show abstract

“…The goal is to maximize the influence values received over T rounds, or equivalently, to minimize the cumulative regret compared with the optimal seed set that generates the largest influence. The most widely studied feedback in the literature is the edge-level feedback (Chen, Wang, and Yuan 2013;Chen et al 2016;Wang and Chen 2017;Wen et al 2017;Wu et al 2019), where the learner can observe whether an edge passes through the information received by its start point. The node-level feedback was only investigated very recently in (Vaswani et al 2015;Li et al 2020), where the learner can only observe which nodes receive the information at each time step during a diffusion process.…”

Section: Introductionmentioning

confidence: 99%

“…OIM has been studied extensively in the literature. For edge-level feedback, existing work (Chen, Wang, and Yuan 2013;Lei et al 2015;Chen et al 2016;Wang and Chen 2017;Wen et al 2017;Wu et al 2019) present both theoretical and heuristic results. The node-level feedback was first proposed in (Vaswani et al 2015).…”

Section: Introductionmentioning

confidence: 99%

Online Influence Maximization with Node-level Feedback Using Standard Offline Oracles

Zhang¹,

Chen²,

Sun³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We study the online influence maximization (OIM) problem in social networks, where in multiple rounds the learner repeatedly chooses seed nodes to generate cascades, observes the cascade feedback, and gradually learns the best seeds that generate the largest cascade. We focus on two major challenges in this paper. First, we work with node-level feedback instead of edge-level feedback. The edge-level feedback reveals all edges that pass through information in a cascade, where the node-level feedback only reveals the activated nodes with timestamps. The node-level feedback is arguably more realistic since in practice it is relatively easy to observe who is influenced but very difficult to observe from which relationship (edge) the influence comes from. Second, we use standard offline oracle instead of offline pair-oracle. To compute a good seed set for the next round, an offline pairoracle finds the best seed set and the best parameters within the confidence region simultaneously, and such an oracle is difficult to compute due to the combinatorial core of OIM problem. So we focus on how to use the standard offline influence maximization oracle which finds the best seed set given the edge parameters as input. In this paper, we resolve these challenges for the two most popular diffusion models, the independent cascade (IC) and the linear threshold (LT) model. For the IC model, the past research only achieves edge-level feedback, while we present the first O( √ T )-regret algorithm for the node-level feedback. For the first challenge above, we apply a novel adaptation of the maximum likelihood estimation (MLE) approach to learn the graph parameters and its confidence region (a confidence ellipsoid). For the second challenge, we adjust the update procedure to dissect the confidence ellipsoid into confidence intervals on each parameter, so that the standard offline influence maximization oracle is enough. For the LT model, a recent study only provides an OIM solution that meets the first challenge but still requires a pair-oracle. In this paper, we apply a similar technique as in the IC model to replace the pair-oracle with a standard oracle while maintaining O( √ T )-regret.

show abstract

Factorization Bandits for Online Influence Maximization

Cited by 26 publications

References 28 publications

Real-Time Influence Maximization in a RTB Setting

Real-Time Influence Maximization in a RTB Setting

Realistic influence maximization based on followers score and engagement grade on instagram

Online Influence Maximization with Node-level Feedback Using Standard Offline Oracles

Contact Info

Product

Resources

About