{"id":77127,"date":"2019-07-22T14:21:52","date_gmt":"2019-07-22T14:21:52","guid":{"rendered":"https:\/\/essays.homeworkacetutors.com\/trust-inference-model-proposal\/"},"modified":"2019-07-22T14:21:52","modified_gmt":"2019-07-22T14:21:52","slug":"trust-inference-model-proposal","status":"publish","type":"post","link":"https:\/\/www.colapapers.com\/us\/trust-inference-model-proposal\/","title":{"rendered":"Trust Inference Model Proposal"},"content":{"rendered":"
\n

(step1-13 in Alg. 4) in the continu-ous case. For advogato<\/em> data set, we directly report the results on all the six snapshots (i.e., advogato-1<\/em>, . . . , advogato-6<\/em>). For PGP<\/em>, we use its subsets to study the scalability. The result is shown in Fig. 6, which is consistent with the complex-ity analysis in Section 4.3. As we can see from the figure, MATRI scales linearly wrt to both n<\/em> and |K<\/em>|, indicating that it is suitable for large-scale applications. The scalability result for the binary case is similar, and we omit the figures for brevity.<\/p>\n

\"\"\"\"<\/p>\n

    \n
  1. (b) (c) (d)<\/strong><\/li>\n<\/ol>\n

    Fig. 3. Scalability of the proposed MATRI for continuous case. MATRI scales linearly wrt the data size (n<\/em> and |K<\/em>|). (a) Wall-clock time vs. n<\/em> on advogato<\/em>. (b) Wall-clock time vs. |K<\/em>| on advogato<\/em>. (c) Wall-clock time vs. n<\/em> on PGP<\/em>. (d) Wall-clock time vs. |K<\/em>| on PGP<\/em>.<\/p>\n

    \"\"<\/p>\n

    Fig. 4. Comparisons of alternative solutions of MATRI. Compared to MATRI-AA, MATRI-SS and MATRI-AS are more than 10x<\/em> faster while preserving more than 90% accuracy on both data sets. (a) advogato<\/em> data set. (b) PGP<\/em> data set.<\/p>\n

    (C)<\/em> Comparisons of the Alternatives<\/em> of<\/em> MATRI. As men-tioned before, the stochastic gradient descent method (SGD) could also be used for the continuous trust inference prob-lem in computing propagation vector and solving Eq. (5). We now experimentally evaluate the efficiency of all the four alternatives of MATRI. We use MATRI-AA to denote the original MATRI, MATRI-SA to denote the case when we use SGD in the propagation step, MATRI-AS.<\/p>\n

    VI<\/strong> RELATED WORK<\/strong><\/p>\n

    In this section, we briefly review related work, includ-ing trust propagation models, multi-aspect trust inference models, etc.<\/p>\n

    Trust Propagation Models.<\/strong> To date, a large body of trust inference models are based on trust propagation where trust is propagated along connected users in the trust net-work, i.e., the web of locally-generated trust ratings. Based on the interpretation of trust propagation, we further cate-gorize these models into two classes: path interpretation<\/em> and component interpretation<\/em>.The proposed MATRI integrates the trust propagation with two other important properties, i.e., the multi-aspect of trust and trust bias. In addition, our multi-aspect model offers a natural way to speed up on-line query response; as well as to mitigate the sparsity or coverage problem in trust inference where some trustor and trustee might not be connected with each other \u2013 both are known limitations with the current trust propagation models [10].<\/p>\n

    Multi-Aspect Trust Inference Models.<\/strong> Social scientists have explored the multi-aspect property of trust for several years [8]. In computer science, there also exist a few trust inference models that explicitly<\/em> explores the trust propagation.<\/p>\n

    Trust Bias in Trust Inference.<\/strong> In sociology, it was dis-covered a long time ago that trust bias<\/em> is an integral part in the final trust decision [9]. Nonetheless, this important aspect has been largely ignored in most of the existing trust inference models. One exception is from Nguyen et al<\/em>. [13], which learns the importance of several trust bias related features derived from a social trust framework. Recently, Mishra et al<\/em>. [25] propose an iterative algorithm to compute trust bias. Different from these existing works, our focus is to incorporate various types of trust bias as specified factors\/aspects to increase the accuracy of trust inference.<\/p>\n

    VII <\/strong> CONCLUSION<\/strong><\/p>\n

    In this paper, we have proposed a trust inference model, as well as a family of algorithms to apply the model to both continuous and binary inference scenarios. The basic idea of the proposed MATRI is to leverage the multi-aspect property of trust by characterizing several aspects\/factors for each trustor and trustee based on the existing trust relationships. In addition, MATRI incorporates the trust propagation and trust bias; and further learns their rela-tive weights. By integrating all these important properties, our experimental evaluations on real benchmark data sets show that MATRI leads to significant improvement over several benchmark approaches in prediction accuracy, for both quantifying numerical trustworthiness scores and pre-dicting binary trust\/distrust signs. The proposed MATRI is also nimble \u2013 it is up to 7 orders of magnitude faster than the existing trust propagation methods in the on-line query response, and in the meanwhile it enjoys the linear scalabil-ity for the pre-computational stage in both time and space. Future work includes investigating the capability of MATRI to address the trust dynamics.<\/p>\n

    REFERENCES<\/strong><\/p>\n

      \n
    1. C. Ziegler and G. Lausen, \u201cPropagation models for trust and distrust in social networks,\u201d Inform. Syst. Front.<\/em>, vol. 7, no. 4, pp.337\u2013358, 2005.<\/li>\n
    2. A. J\u00f8sang and R. Ismail, \u201cThe Beta reputation system,\u201d in Proc.<\/em> 15th Bled Electron. Comm. Conf.<\/em>, vol. 160. Bled, Slovenia, Jun. 2002.<\/li>\n
    3. S. D. Kamvar, M. T. Schlosser, and H. Garcia-Molina, \u201cThe Eigentrust algorithm for reputation management in P2P net-works,\u201d in Proc. 12th Int. Conf. WWW<\/em>, Budapest, Hungary, 2003, pp.640\u2013651.<\/li>\n
    4. M. Richardson, R. Agrawal, and P. Domingos, \u201cTrust management for the semantic web,\u201d in Proc. 2nd ISWC<\/em>, Sanibel Island, FL, USA, 2003, pp. 351\u2013368.<\/li>\n<\/ol>\n
        \n
      1. D. Cartwright and F. Harary, \u201cStructural balance: A generalization of Heider\u2019s theory,\u201d Psychol. Rev.<\/em>, vol. 63, no. 5, pp. 277\u2013293, 1956.<\/li>\n
      2. G. Liu, Y. Wang, and M. Orgun, \u201cTrust transitivity in complex social networks,\u201d in Proc. AAAI<\/em>, 2011, pp. 1222\u20131229.<\/li>\n
      3. D. Gefen, \u201cReflections on the dimensions of trust and trustwor-thiness among online consumers,\u201d ACM SIGMIS Database<\/em>, vol. 33, no. 3, pp. 38\u201353, 2002.<\/li>\n
      4. D. Sirdeshmukh, J. Singh, and B. Sabol, \u201cConsumer trust, value, and loyalty in relational exchanges,\u201d J. Marketing<\/em>, vol. 66, no. 1, pp.15\u201337, 2002.<\/li>\n
      5. A. Tversky and D. Kahneman, \u201cJudgment under uncertainty: Heuristics and biases,\u201d Sci.<\/em>, vol. 185, no. 4157, pp. 1124\u20131131, 1974.<\/li>\n
      6. Y. Yao, H. Tong, F. Xu, and J. Lu, \u201cSubgraph extraction for trust inference in social networks,\u201d in Proc. IEEE\/ACM Int. Conf.<\/em> ASONAM<\/em>, Istanbul, Turkey, 2012, pp. 163\u2013170.<\/li>\n
      7. L. Xiong and L. Liu, \u201cPeertrust: Supporting reputation-based trust for peer-to-peer electronic communities,\u201d IEEE Trans. Knowl. Data<\/em> Eng.<\/em>, vol. 16, no. 7, pp. 843\u2013857, Jul. 2004.<\/li>\n
      8. J. Tang, H. Gao, and H. Liu, \u201cmTrust: Discerning multi-faceted trust in a connected world,\u201d in Proc. 5th ACM Int. Conf. WSDM<\/em>, Washingtion, DC, USA, 2012, pp. 93\u2013102.<\/li>\n
      9. V. Nguyen, E. Lim, J. Jiang, and A. Sun, \u201cTo trust or not to trust? Predicting online trusts using trust antecedent framework,\u201d in Proc. 9th IEEE ICDM<\/em>, Miami, FL, USA, 2009, pp. 896\u2013901.<\/li>\n
      10. Y. Koren, \u201cFactorization meets the neighborhood: A multifaceted collaborative filtering model,\u201d in Proc. 14th ACM SIGKDD Int.<\/em> Conf. KDD<\/em>, New York, NY, USA, 2008, pp. 426\u2013434.<\/li>\n
      11. R. Guha, R. Kumar, P. Raghavan, and A. Tomkins, \u201cPropagation of trust and distrust,\u201d in Proc. 13th Int. Conf. WWW<\/em>, New York, NY, USA, 2004, pp. 403\u2013412.<\/li>\n
      12. Y. Koren, R. Bell, and C. Volinsky, \u201cMatrix factorization techniques for recommender systems,\u201d Comput.<\/em>, vol. 42, no. 8, pp. 30\u201337, 2009.<\/li>\n
      13. P. Massa and P. Avesani, \u201cControversial users demand local trust metrics: An experimental study on epinions. com community,\u201d in Proc. 20th Nat. Conf. AAAI<\/em>, 2005, pp. 121\u2013126.<\/li>\n
      14. B. Lang, \u201cA computational trust model for access control in P2P,\u201d Sci. China Inform. Sci.<\/em>, vol. 53, no. 5, pp. 896\u2013910, 2010.<\/li>\n
      15. R. Bell, Y. Koren, and C. Volinsky, \u201cModeling relationships at mul-tiple scales to improve accuracy of large recommender systems,\u201d in Proc. 13th ACM SIGKDD Int. Conf. KDD<\/em>, New York, NY, USA, 2007, pp. 95\u2013104.<\/li>\n
      16. H. Ma, M. Lyu, and I. King, \u201cLearning to recommend with trust and distrust relationships,\u201d in Proc. 3rd ACM Conf. RecSys<\/em>, New York, NY, USA, 2009, pp. 189\u2013196.<\/li>\n
      17. A. Buchanan and A. Fitzgibbon, \u201cDamped Newton algorithms for matrix factorization with missing data,\u201d in Proc. IEEE CVPR<\/em>, vol. 2. Washington, DC, USA, 2005, pp. 316\u2013322.<\/li>\n
      18. X. Liu, A. Datta, K. Rzadca, and E. Lim, \u201cStereotrust: A group based personalized trust model,\u201d in Proc. 18th ACM CIKM<\/em>, Hong Kong, China, 2009, pp. 7\u201316.<\/li>\n
      19. D. Watts and S. Strogatz, \u201cCollective dynamics of \u2019small-world\u2019 networks,\u201d Nature<\/em>, vol. 393, no. 6684, pp. 440\u2013442, 1998.<\/li>\n
      20. J. Leskovec, J. Kleinberg, and C. Faloutsos, \u201cGraphs over time: Densification laws, shrinking diameters and possible explana-tions,\u201d in Proc. 11th ACM SIGKDD Int. Conf. KDD<\/em>, Chicago, IL, USA, 2005, pp. 177\u2013187.<\/li>\n
      21. C.-W. Hang, Y. Wang, and M. P. Singh, \u201cOperators for propagating trust and their evaluation in social networks,\u201d in Proc. 8th Int.<\/em> Conf. AAMAS<\/em>, Budapest, Hungary, 2009, pp. 1025\u20131032.<\/li>\n
      22. J. Leskovec, D. Huttenlocher, and J. Kleinberg, \u201cPredicting posi-tive and negative links in online social networks,\u201d in Proc. 19th<\/em> Int. Conf. WWW<\/em>, Raleigh, NC, USA, 2010, pp. 641\u2013650.<\/li>\n
      23. Y. Wang and M. P. Singh, \u201cTrust representation and aggregation in a distributed agent system,\u201d in Proc. 21st Nat. Conf. AAAI<\/em>, 2006, pp.1425\u20131430.<\/li>\n
      24. Y. Wang and M. P. Singh, \u201cFormal trust model for multiagent systems,\u201d in Proc. 20th IJCAI<\/em>, San Francisco, CA, USA, 2007, pp.1551\u20131556.<\/li>\n
      25. C. Hsieh, K. Chiang, and I. Dhillon, \u201cLow rank modeling of signed networks,\u201d in Proc. 18th ACM SIGKDD Int. Conf. KDD<\/em>, Beijing, China, 2012, pp. 507\u2013515.<\/li>\n
      26. K.-Y. Chiang, N. Natarajan, A. Tewari, and I. S. Dhillon, \u201cExploiting longer cycles for link prediction in signed net-works,\u201d in Proc. 20th ACM CIKM<\/em>, Glasgow, Scotland, U.K., 2011, pp.1157\u20131162.<\/li>\n<\/ol>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

        (step1-13 in Alg. 4) in the continu-ous case. For advogato data set, we directly report the results on all the six snapshots (i.e., advogato-1, . . . , advogato-6). For PGP, we use its subsets to study the scalability. The result is shown in Fig. 6, which is consistent with the complex-ity analysis in Section […]<\/p>\n","protected":false},"author":8,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[9869,9870,9889,3953,9940,9799,9939],"class_list":["post-77127","post","type-post","status-publish","format-standard","hentry","tag-au","tag-complete-the-assignment-in-a-page-paper","tag-in-1050-word-essay","tag-need-help-writing-a-masters-thesis","tag-online-class-course-exam-help","tag-research-essay-pro","tag-write-my-essay-homework-due-in-hours"],"_links":{"self":[{"href":"https:\/\/www.colapapers.com\/us\/wp-json\/wp\/v2\/posts\/77127","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.colapapers.com\/us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.colapapers.com\/us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.colapapers.com\/us\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/www.colapapers.com\/us\/wp-json\/wp\/v2\/comments?post=77127"}],"version-history":[{"count":0,"href":"https:\/\/www.colapapers.com\/us\/wp-json\/wp\/v2\/posts\/77127\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.colapapers.com\/us\/wp-json\/wp\/v2\/media?parent=77127"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.colapapers.com\/us\/wp-json\/wp\/v2\/categories?post=77127"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.colapapers.com\/us\/wp-json\/wp\/v2\/tags?post=77127"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}