國立虎尾科技大學 |

登入

回首頁

Deep collective inference.

Moore, John A.

Deep collective inference.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Deep collective inference./
作者:	Moore, John A.
面頁冊數:	1 online resource (54 pages)
附註:	Source: Masters Abstracts International, Volume: 56-03.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9781369643121

Deep collective inference.
Moore, John A.

Deep collective inference. - 1 online resource (54 pages)

Source: Masters Abstracts International, Volume: 56-03.

Thesis (M.S.)--Purdue University, 2016.

Includes bibliographical references

Collective inference is widely used to improve classification in network datasets.

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

Mode of access: World Wide Web

ISBN: 9781369643121Subjects--Topical Terms:

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

554714
Electronic books.

Deep collective inference.
LDR:02670ntm a2200505K 4500 001 915272
005 20180727125211.5
006 m o u
007 cr mn||||a|a||
008 190606s2016 xx obm 000 0 eng d
020 $a 9781369643121
035 $a (MiAaPQ)AAI10248759
035 $a (MiAaPQ)purdue:20934
035 $a AAI10248759
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Moore, John A. $3 1188580
245 1 0 $a Deep collective inference.
264 0 $c 2016
300 $a 1 online resource (54 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: Masters Abstracts International, Volume: 56-03.
500 $a Adviser: Jennifer Neville.
502 $a Thesis (M.S.)--Purdue University, 2016.
504 $a Includes bibliographical references
520 $a Collective inference is widely used to improve classification in network datasets.
520 $a However, despite recent advances in deep learning and the successes of recurrent neural.
520 $a networks (RNNs), researchers have only just recently begun to study how to apply.
520 $a RNNs to heterogeneous graph and network datasets. There has been recent work on.
520 $a using RNNs for unsupervised learning in networks (e.g., graph clustering, node embedding).
520 $a and for prediction (e.g., link prediction, graph classification), but there has.
520 $a been little work on using RNNs for node-based relational classification tasks. In this.
520 $a paper, we provide an end-to-end learning framework using RNNs for collective inference.
520 $a Our main insight is to transform a node and its set of neighbors into an.
520 $a unordered sequence (of varying length) and use an LSTM-based RNN to predict the.
520 $a class label as the output of that sequence. We develop a collective inference method,
520 $a which we refer to as Deep Collective Inference (DCI), that uses semi-supervised learning.
520 $a in partially-labeled networks and two label distribution correction mechanisms.
520 $a for imbalanced classes. We compare to several alternative methods on seven network.
520 $a datasets. DCI achieves up to a 12% reduction in error compared to the best.
520 $a alternative and a 25% reduction in error on average over all methods, for all label.
520 $a proportions.
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 Purdue University. $b Computer Sciences. $3 1179390
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10248759 $z click for full text (PQDT)

筆 0 讀者評論

多媒體

評論

新增評論分享你的心得

Export

取書館別