Sharan, U (Sharan, Umang); Neville, J (Neville, Jennifer) Temporal-Relational Classifiers for Prediction in Evolving Domains ICDM 2008: EIGHTH IEEE INTERNATIONAL CONFERENCE ON DATA MINING, PROCEEDINGS: 540-549 2008

[Eugene Garfield]

Author(s): Sharan, U (Sharan, Umang); Neville, J (Neville, Jennifer) 

Editor(s): Gunopulos, D; Turini, F; Zaniolo, C; Ramakrishnan, N; Wu, XD 

Book Author(s): Giannotti, F 

Title: Temporal-Relational Classifiers for Prediction in Evolving Domains 

Source: ICDM 2008: EIGHTH IEEE INTERNATIONAL CONFERENCE ON DATA MINING, 
PROCEEDINGS: 540-549 2008 

Book series title: IEEE International Conference on Data Mining 

Language: English 

Document Type: Proceedings Paper 

Conference Title: 8th IEEE International Conference on Data Mining 

Conference Date: DEC 15-19, 2008 

Conference Location: Pisa, ITALY 

Conference Sponsors: IEEE.; Yahoo Res.; WIND.; Microsoft.; Ask com.; IBM.; 
Natl Sci Fdn.; coop.; base.; Univ Pisa.; Brite.; Comune Pisa.; Prov Pisa.; 
Prov Lucca.; Inst Sci & Tecnol Informazione.; Consiglio Nazl Ric.; 
GeoPKDD.; Camera Commercia Pisa. 

Abstract: Many relational domains contain temporal information and 
dynamics that are important to model (e.g., social networks, protein 
networks). However past work in relational learning has focused primarily 
on modeling static "snap-shots" of the data and has largely ignored the 
temporal dimension of these data. In. this work we extend relational 
techniques to temporally-evolving domains and outline a representational 
framework that is capable of modeling both temporal and relational 
dependencies in the data. We develop efficient learning and inference 
techniques within the framework by considering a restricted set of 
temporal-relational dependencies and using parameter-tying methods to 
generalize across relationships and entities. More specifically, we model 
dynamic relational data with a two-phase process, first summarizing the 
temporal-relational information with kernel smoothing, and then moderating 
attribute dependencies with the summarized relational information. We 
develop a number of novel temporal-relational models using the framework 
and then show that the current approaches to modeling static relational 
data are special cases within the framework. We compare the new models to 
the competing static relational methods on three real-world datasets and 
show that the temporal-relational models consistently outperform the 
relational models that ignore temporal information-achieving significant 
reductions in error ranging from 15% to 70%. 

Addresses: [Sharan, Umang] Purdue Univ, Dept Comp Sci, W Lafayette, IN 
47907 USA 

Reprint Address: Sharan, U, Purdue Univ, Dept Comp Sci, W Lafayette, IN 
47907 USA. 

Cited Reference Count: 24 

Times Cited: 0 

Publisher: IEEE COMPUTER SOC 

Publisher Address: 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, 
CA 90720-1264 USA 

ISSN: 1550-4786 

ISBN: 978-0-7695-3502-9 

29-char Source Abbrev.: IEEE DATA MINING 

Source Item Page Count: 10 

ISI Document Delivery No.: BJA60 

AMITAY E
Trend detection through temporal link analysis 
JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY 
55 : 1270 DOI 10.1002/asi.20082 2004 

BHARAT K
P IEEE INT C DAT MIN : 2001 

BLAU H
0128 U MASS AMH COMP : 2001 

CAI D
P 9 EUR C PRINC PRAC : 2005 

CHAKRABARTI S
P ACM SIGMODD INT C : 1998 

CORTES C
P 4 INT S INT DAT AN : 2001 

DOMINGOS P
On the optimality of the simple Bayesian classifier under zero-one loss 
MACHINE LEARNING 29 : 103 1997 

DOMINGOS P
P 7 ACM SIGKDD INT C : 2001 

EGGHE L
J AM SOC INF SCI TEC 52 : 2001 

FRIEDMAN N
P 16 INT JOINT C ART : 1999 

GARFIELD E
CITATION ANALYSIS AS A TOOL IN JOURNAL EVALUATION - JOURNALS CAN BE RANKED 
BY FREQUENCY AND IMPACT OF CITATIONS FOR SCIENCE POLICY STUDIES 
SCIENCE 178 : 471 1972 

GHAHRAMANI Z
Learning dynamic Bayesian networks 
ADAPTIVE PROCESSING OF SEQUENCES AND DATA STRUCTURES 1387 : 168 1998 

GUESTRIN C
P INT JOINT C ART IN : 2003 

GUO F
P 24 INT C MACH LEAR : 2007 

J COMPUTATIONAL GRAP : 2006 

JENSEN D
P 19 INT C MACH LEAR : 2002 

KUMAR R
P 12 INT WWW C : 2003 

MCCALLUM A
P 16 INT JOINT C ART : 1999 

NEVILLE J
P 11 ACM SIGKDD INT : 2005 

NEVILLE J
P 3 IEEE INT C DAT M : 2003 

NEVILLE J
P 9 ACM SIGKDD INT C : 2003 

PERLICH C
P 9 ACM SIGKDD INT C : 2003 

SNIJDERS TAB
J SOCIAL STRUCTURE 3 : 2 2002 

TASKAR B
P 18 C UNC ART INT : 2002