AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
We propose a randomized algorithm for influence estimation in continuous-time diffusion networks

Scalable Influence Estimation in Continuous-Time Diffusion Networks.

neural information processing systems, (2013): 3147-3155

Cited by: 302|Views422
EI WOS

Abstract

If a piece of information is released from a media site, can we predict whether it may spread to one million web pages, in a month ? This influence estimation problem is very challenging since both the time-sensitive nature of the task and the requirement of scalability need to be addressed simultaneously. In this paper, we propose a rand...More

Code:

Data:

0
Introduction
  • Motivated by applications in viral marketing [1], researchers have been studying the influence maximization problem: find a set of nodes whose initial adoptions of certain idea or product can trigger, in a time window, the largest expected number of follow-ups.
  • For this purpose, it is essential to accurately and efficiently estimate the number of follow-ups of an arbitrary set of source nodes within the given time window.
  • Such time-sensitive requirement renders those algorithms which only consider static information, such as network topologies, inappropriate in this context
Highlights
  • Motivated by applications in viral marketing [1], researchers have been studying the influence maximization problem: find a set of nodes whose initial adoptions of certain idea or product can trigger, in a time window, the largest expected number of follow-ups
  • We evaluate the accuracy of the estimated influence given by CONTINEST and investigate the performance of influence maximization on synthetic and real networks
  • Any consistent improvement in influence estimation can lead to significant improvement to the overall influence estimation and maximization task, which is further confirmed by Figures 3(b) and 3(c) where we evaluate the influence of the selected nodes in the same spirit as influence estimation: the true influence is calculated as the total number of distinct nodes infected before T based on C(u) of the selected nodes
  • We propose a randomized influence estimation algorithm in continuous-time diffusion networks, which can scale up to networks of millions of nodes while significantly improves over previous stateof-the-arts in terms of the accuracy of the estimated influence and the quality of the selected nodes in maximizing the influence
  • We show that our approach significantly outperforms the state-of-the-art methods in terms of both speed and solution quality
  • It will be interesting to apply the current algorithm to other tasks like influence minimization and manipulation, and design scalable algorithms for continuous-time models other than the independent cascade model
Methods
  • The authors evaluate the accuracy of the estimated influence given by CONTINEST and investigate the performance of influence maximization on synthetic and real networks.
  • Synthetic network generation.
  • The authors generate three types of Kronecker networks [20]: (i) coreperiphery networks, which mimic the information diffusion traces in real world networks [21], (ii) random networks ([0.5 0.5; 0.5 0.5]), typically used in physics and graph theory [22] and (iii) hierarchical networks ([0.9 0.1; 0.1 0.9]) [10].
  • The authors use the Weibull distribution [16], f (t; α, β)
Results
  • The authors show that the approach significantly outperforms the state-of-the-art methods in terms of both speed and solution quality.
Conclusion
  • The authors propose a randomized influence estimation algorithm in continuous-time diffusion networks, which can scale up to networks of millions of nodes while significantly improves over previous stateof-the-arts in terms of the accuracy of the estimated influence and the quality of the selected nodes in maximizing the influence.
  • It will be interesting to apply the current algorithm to other tasks like influence minimization and manipulation, and design scalable algorithms for continuous-time models other than the independent cascade model
Funding
  • Our work is supported by NSF/NIH BIGDATA 1R01GM108341-01, NSF IIS1116886, NSF IIS1218749, NSFC 61129001, a DARPA Xdata grant and Raytheon Faculty Fellowship of Gatech
Reference
  • David Kempe, Jon Kleinberg, and Eva Tardos. Maximizing the spread of influence through a social network. In KDD, pages 137–146, 2003.
    Google ScholarLocate open access versionFindings
  • Wei Chen, Yajun Wang, and Siyu Yang. Efficient influence maximization in social networks. In KDD, pages 199–208, 2009.
    Google ScholarLocate open access versionFindings
  • Wei Chen, Yifei Yuan, and Li Zhang. Scalable influence maximization in social networks under the linear threshold model. In ICDM, pages 88–97, 2010.
    Google ScholarLocate open access versionFindings
  • Amit Goyal, Francesco Bonchi, and Laks V. S. Lakshmanan. A data-based approach to social influence maximization. Proc. VLDB Endow., 5, 2011.
    Google ScholarLocate open access versionFindings
  • Jure Leskovec, Andreas Krause, Carlos Guestrin, Christos Faloutsos, Jeanne M. VanBriesen, and Natalie S. Glance. Cost-effective outbreak detection in networks. In KDD, pages 420–429, 2007.
    Google ScholarLocate open access versionFindings
  • Matthew Richardson and Pedro Domingos. Mining knowledge-sharing sites for viral marketing. In KDD, pages 61–70, 2002.
    Google ScholarLocate open access versionFindings
  • Manuel Gomez-Rodriguez and Bernhard Scholkopf. Influence maximization in continuous time diffusion networks. In ICML ’12, 2012.
    Google ScholarLocate open access versionFindings
  • Nan Du, Le Song, Alexander J. Smola, and Ming Yuan. Learning networks of heterogeneous influence. In NIPS, 2012.
    Google ScholarLocate open access versionFindings
  • Nan Du, Le Song, Hyenkyun Woo, and Hongyuan Zha. Uncover topic-sensitive information diffusion networks. In AISTATS, 2013.
    Google ScholarLocate open access versionFindings
  • Manuel Gomez-Rodriguez, David Balduzzi, and Bernhard Scholkopf. Uncovering the temporal dynamics of diffusion networks. In ICML, pages 561–568, 2011.
    Google ScholarLocate open access versionFindings
  • Manuel Gomez-Rodriguez, Jure Leskovec, and Bernhard Scholkopf. Structure and Dynamics of Information Pathways in On-line Media. In WSDM, 2013.
    Google ScholarLocate open access versionFindings
  • Ke Zhou, Le Song, and Hongyuan Zha. Learning social infectivity in sparse low-rank networks using multi-dimensional hawkes processes. In Artificial Intelligence and Statistics (AISTATS), 2013.
    Google ScholarLocate open access versionFindings
  • Ke Zhou, Hongyuan Zha, and Le Song. Learning triggering kernels for multi-dimensional hawkes processes. In International Conference on Machine Learning(ICML), 2013.
    Google ScholarLocate open access versionFindings
  • Manuel Gomez-Rodriguez, Jure Leskovec, and Bernhard Scholkopf. Modeling information propagation with survival theory. In ICML, 2013.
    Google ScholarLocate open access versionFindings
  • Shuanghong Yang and Hongyuan Zha. Mixture of mutually exciting processes for viral diffusion. In International Conference on Machine Learning(ICML), 2013.
    Google ScholarLocate open access versionFindings
  • Jerald F. Lawless. Statistical Models and Methods for Lifetime Data. Wiley-Interscience, 2002.
    Google ScholarLocate open access versionFindings
  • Edith Cohen. Size-estimation framework with applications to transitive closure and reachability. Journal of Computer and System Sciences, 55(3):441–453, 1997.
    Google ScholarLocate open access versionFindings
  • GL Nemhauser, LA Wolsey, and ML Fisher. An analysis of approximations for maximizing submodular set functions. Mathematical Programming, 14(1), 1978.
    Google ScholarLocate open access versionFindings
  • Andreas Krause. Ph.D. Thesis. CMU, 2008.
    Google ScholarLocate open access versionFindings
  • Jure Leskovec, Deepayan Chakrabarti, Jon M. Kleinberg, Christos Faloutsos, and Zoubin Ghahramani. Kronecker graphs: An approach to modeling networks. JMLR, 11, 2010.
    Google ScholarLocate open access versionFindings
  • Manuel Gomez-Rodriguez, Jure Leskovec, and Andreas Krause. Inferring networks of diffusion and influence. In KDD, 2010.
    Google ScholarLocate open access versionFindings
  • David Easley and Jon Kleinberg. Networks, Crowds, and Markets: Reasoning About a Highly Connected World. Cambridge University Press, 2010.
    Google ScholarFindings
  • Jure Leskovec, Lars Backstrom, and Jon M. Kleinberg. Meme-tracking and the dynamics of the news cycle. In KDD, 2009.
    Google ScholarLocate open access versionFindings
  • Praneeth Netrapalli and Sujay Sanghavi. Learning the graph of epidemic cascades. In SIGMETRICS/PERFORMANCE, pages 211–222. ACM, 2012.
    Google ScholarLocate open access versionFindings
  • Wei Chen, Chi Wang, and Yajun Wang. Scalable influence maximization for prevalent viral marketing in large-scale social networks. In KDD ’10, pages 1029–1038, 2010.
    Google ScholarLocate open access versionFindings
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科