國立虎尾科技大學 |

Link Prediction in dynamic networks.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Link Prediction in dynamic networks./
作者:	Salem Narasimhan, Jeyanthi.
面頁冊數:	1 online resource (164 pages)
附註:	Source: Dissertation Abstracts International, Volume: 77-08(E), Section: B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9781339553078

Link Prediction in dynamic networks.
Salem Narasimhan, Jeyanthi.

Link Prediction in dynamic networks. - 1 online resource (164 pages)

Source: Dissertation Abstracts International, Volume: 77-08(E), Section: B.

Thesis (Ph.D.)--Washington State University, 2015.

Includes bibliographical references

Link Prediction in dynamic networks aims to model the patterns of relationship formation between any two agents in a multi-agent network for predicting the future links. We present three contributions to the state-of-the-art supervised link prediction (SLP) solutions, approaching the problem from three mutually exclusive, nonetheless, related perspectives in dynamic networks.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781339553078Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Link Prediction in dynamic networks.
LDR:03339ntm a2200349K 4500 001 913623
005 20180622095234.5
006 m o u
007 cr mn||||a|a||
008 190606s2015 xx obm 000 0 eng d
020 $a 9781339553078
035 $a (MiAaPQ)AAI10043071
035 $a (MiAaPQ)wsu:11527
035 $a AAI10043071
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Salem Narasimhan, Jeyanthi. $3 1186532
245 1 0 $a Link Prediction in dynamic networks.
264 0 $c 2015
300 $a 1 online resource (164 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 77-08(E), Section: B.
500 $a Adviser: Lawrence B. Holder.
502 $a Thesis (Ph.D.)--Washington State University, 2015.
504 $a Includes bibliographical references
520 $a Link Prediction in dynamic networks aims to model the patterns of relationship formation between any two agents in a multi-agent network for predicting the future links. We present three contributions to the state-of-the-art supervised link prediction (SLP) solutions, approaching the problem from three mutually exclusive, nonetheless, related perspectives in dynamic networks.
520 $a First, we propose Feature Evolution based LP (FELP), which uses a two-step solution strategy. The initial step consists of constructing novel yet simple features using a combination of domain and topological attributes of the network. Next, we perform unconstrained node selection to identify potential candidates for prediction by any generic two-class learner. Our experiments on a real-world large collaboration network show the effectiveness of our framework over a sophisticated baseline.
520 $a Second, we predict links between two connected components in a dynamic network, using intuitive network topological features, a novel feature processing technique especially when time is involved, and two different ways of learning a classifier based on the amount of historical data collected. Based on extensive experiments on two real-world collaboration networks, our History based Eccentric LP (HELP) method achieves up to 13\% improvement over the baseline on edges with no historical data; on edges with historical data, we observed up to 3x improvement over the baseline. Since SLP is an extreme class-skew problem, we analyze the behavior of two leading performance measures for imbalanced learning, and prove the conditions for their dissonance. We also prove and validate the effect of relative increase in imbalance on the magnitude of a performance score.
520 $a Third, to address the inherent class-skew, we propose Minority Credit based LP (MCLP) that uses one-class learning on only minority class examples. Moreover, our framework can extract additional data from the network evolution thereby dealing with the data scarcity. Our experiments on a real-world online social network show that the additional data and one-class learning allow MCLP to further improve performance over the previous approaches.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Washington State University. $b Computer Science. $3 1186533
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10043071 $z click for full text (PQDT)