Evolving Influence Maximization in Evolving Networks

Influence Maximization (IM) aims to maximize the number of people that become aware of a product by finding the “best” set of “seed” users to initiate the product advertisement. Unlike most prior arts on the static networks containing fixed number of users, we study the evolving IM in more realistic evolving networks with temporally growing topology. The task of evolving IM, however, is far more challenging over static cases in the sense that the seed selection should consider its impact on future users who will join network during influence diffusion and the probabilities that users influence one another also evolve over time. We address the challenges brought by network evolution through EIM, a newly proposed bandit-based framework that alternates between seed nodes selection and knowledge (i.e., nodes’ growing speed and evolving activation probabilities) learning during network evolution. Remarkably, the EIM framework involves three novel components to handle the uncertainties brought by evolution: (1) A fully adaptive particle learning of nodes’ growing speed for accurately estimating future influenced size, with real growing behaviors delineated by a set of weighted particles. (2) A bandit-based refining method with growing arms to cope with the evolving activation probabilities via growing edges from previous influence diffusion feedbacks. (3) Evo-IMM, an evolving seed selection algorithm, which leverages the Influence Maximization via Martingale (IMM) framework, with the objective to maximize the influence spread to highly attractive users during evolution. Theoretically, the EIM framework returns a regret bound that provably maintains its sublinearity with respect to the growing network size. Empirically, the effectiveness of the EIM framework is also validated with three notable million-scale evolving network datasets possessing complete social relationships and nodes’ joining time. The results confirm the superiority of the EIM framework in terms of an up to 50% larger influenced size over four static baselines.

[1]  Qing Wang,et al.  Online Context-Aware Recommendation with Time Varying Multi-Armed Bandit , 2016, KDD.

[2]  Reynold Cheng,et al.  Online Influence Maximization , 2015, KDD.

[3]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[4]  Philip S. Yu,et al.  Multi-Round Influence Maximization , 2018, KDD.

[5]  Timothy K. Shih,et al.  Grouping Peers Based on Complementary Degree and Social Relationship using Genetic Algorithm , 2018, TOIT.

[6]  Wei Chen,et al.  Combinatorial Multi-Armed Bandit: General Framework and Applications , 2013, ICML.

[7]  Éva Tardos,et al.  Maximizing the Spread of Influence through a Social Network , 2015, Theory Comput..

[8]  Shaojie Tang,et al.  Discount Allocation for Revenue Maximization in Online Social Networks , 2018, MobiHoc.

[9]  Shou-De Lin,et al.  A Learning-based Framework to Handle Multi-round Multi-party Influence Maximization on Social Networks , 2015, KDD.

[10]  Xinbing Wang,et al.  Maximizing Influence Diffusion over Evolving Social Networks , 2019, SocialSens@CPSIoTWeek.

[11]  Maria A. Kazandjieva,et al.  A high-resolution human contact network for infectious disease transmission , 2010, Proceedings of the National Academy of Sciences.

[12]  Xiaokui Xiao,et al.  Influence maximization: near-optimal time complexity meets practical efficiency , 2014, SIGMOD Conference.

[13]  Edith Cohen,et al.  Sketch-based Influence Maximization and Computation: Scaling up with Guarantees , 2014, CIKM.

[14]  Omar Rivasplata,et al.  Subgaussian random variables : An expository note , 2012 .

[15]  Evaggelia Pitoura,et al.  Diffusion Maximization in Evolving Social Networks , 2015, COSN.

[16]  Béla Bollobás,et al.  The Diameter of a Scale-Free Random Graph , 2004, Comb..

[17]  Przemyslaw Kazienko,et al.  Seed Selection for Spread of Influence in Social Networks: Temporal vs. Static Approach , 2014, New Generation Computing.

[18]  Hung T. Nguyen,et al.  Outward Influence and Cascade Size Estimation in Billion-scale Networks , 2017, Proc. ACM Meas. Anal. Comput. Syst..

[19]  Przemyslaw Kazienko,et al.  Compensatory seeding in networks with varying avaliability of nodes , 2013, 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2013).

[20]  Shaojie Tang,et al.  Adaptive Influence Maximization in Dynamic Social Networks , 2015, IEEE/ACM Transactions on Networking.

[21]  Christos Faloutsos,et al.  Long Short Memory Process: Modeling Growth Dynamics of Microscopic Social Connectivity , 2017, KDD.

[22]  John C. S. Lui,et al.  Boosting Information Spread: An Algorithmic Approach , 2016, 2017 IEEE 33rd International Conference on Data Engineering (ICDE).

[23]  Jure Leskovec,et al.  Inferring networks of diffusion and influence , 2010, KDD.

[24]  Xuemin Lin,et al.  Distance-aware influence maximization in geo-social network , 2016, 2016 IEEE 32nd International Conference on Data Engineering (ICDE).

[25]  Wen-Xu Wang,et al.  Reconstructing propagation networks with natural diversity and identifying hidden sources , 2014, Nature Communications.

[26]  Sylvain Lamprier,et al.  Extracting diffusion channels from real-world social data: A delay-agnostic learning of transmission probabilities , 2015, 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[27]  Qing Zhao,et al.  Learning in a Changing World: Restless Multiarmed Bandit With Unknown Dynamics , 2010, IEEE Transactions on Information Theory.

[28]  Xinbing Wang,et al.  GLP: A Novel Framework for Group-Level Location Promotion in Geo-Social Networks , 2018, IEEE/ACM Transactions on Networking.

[29]  Wenhao Yu,et al.  Supplementary material , 2015 .

[30]  Esteban Moro,et al.  Impact of human activity patterns on the dynamics of information diffusion. , 2009, Physical review letters.

[31]  Jianfeng Ma,et al.  Time is What Prevents Everything from Happening at Once: Propagation Time-conscious Influence Maximization , 2017, ArXiv.

[32]  Zheng Wen,et al.  Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback , 2016, NIPS.

[33]  Christos Faloutsos,et al.  Beyond Sigmoids: The NetTide Model for Social Network Growth, and Its Applications , 2016, KDD.

[34]  Huazheng Wang,et al.  Factorization Bandits for Online Influence Maximization , 2019, KDD.

[35]  Chuan Wu,et al.  Online influence maximization in non-stationary Social Networks , 2016, 2016 IEEE/ACM 24th International Symposium on Quality of Service (IWQoS).

[36]  Todd P. Coleman,et al.  Directed Information Graphs , 2012, IEEE Transactions on Information Theory.

[37]  Shaojie Tang,et al.  Adaptive Discount Allocation in Social Networks , 2017, MobiHoc.

[38]  B. Malakooti.  Forecasting , 2013 .

[39]  Zheng Wen,et al.  Influence Maximization with Semi-Bandit Feedback , 2016, ArXiv.

[40]  Xiaokui Xiao,et al.  Influence Maximization in Near-Linear Time: A Martingale Approach , 2015, SIGMOD Conference.

[41]  Jian Pei,et al.  Continuous Influence Maximization: What Discounts Should We Offer to Social Network Users? , 2016, SIGMOD Conference.

[42]  Jure Leskovec,et al.  On the Convexity of Latent Social Network Inference , 2010, NIPS.

[43]  Andrew Harvey,et al.  Forecasting, Structural Time Series Models and the Kalman Filter. , 1991 .

[44]  Jie Tang,et al.  Influence Maximization in Dynamic Social Networks , 2013, 2013 IEEE 13th International Conference on Data Mining.

[45]  Wei Chen,et al.  Scalable influence maximization for prevalent viral marketing in large-scale social networks , 2010, KDD.