TY - CONF
T1 - A kernel conditional independence test for relational data
AU - Lee, Sanghack
AU - Honavar, Vasant
N1 - Funding Information:
The authors are grateful to UAI 2017 anonymous reviewers for their thorough reviews. This research was supported by the Edward Frymoyer Endowed Professorship, the Center for Big Data Analytics and Discovery Informatics at the Pennsylvania State University, and the Sudha Murty Distinguished Visiting Chair in Neurocomputing and Data Science at the Indian Institute of Science.
PY - 2017
Y1 - 2017
N2 - Conditional independence (CI) tests play a central role in statistical inference, machine learning, and causal discovery. Most existing CI tests assume that the samples are independently and identically distributed (i.i.d.). However, this assumption often does not hold in the case of relational data. We define Relational Conditional Independence (RCI), a generalization of CI to the relational setting. We show how, under a set of structural assumptions, we can test for RCI by reducing the task of testing for RCI on non-i.i.d. data to the problem of testing for CI on several data sets each of which consists of i.i.d. samples. We develop Kernel Relational CI test (KRCIT), a nonparametric test as a practical approach to testing for RCI by relaxing the structural assumptions used in our analysis of RCI. We describe results of experiments with synthetic relational data that show the benefits of KRCIT relative to traditional CI tests that don't account for the non-i.i.d. nature of relational data.
AB - Conditional independence (CI) tests play a central role in statistical inference, machine learning, and causal discovery. Most existing CI tests assume that the samples are independently and identically distributed (i.i.d.). However, this assumption often does not hold in the case of relational data. We define Relational Conditional Independence (RCI), a generalization of CI to the relational setting. We show how, under a set of structural assumptions, we can test for RCI by reducing the task of testing for RCI on non-i.i.d. data to the problem of testing for CI on several data sets each of which consists of i.i.d. samples. We develop Kernel Relational CI test (KRCIT), a nonparametric test as a practical approach to testing for RCI by relaxing the structural assumptions used in our analysis of RCI. We describe results of experiments with synthetic relational data that show the benefits of KRCIT relative to traditional CI tests that don't account for the non-i.i.d. nature of relational data.
UR - http://www.scopus.com/inward/record.url?scp=85031095069&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85031095069&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:85031095069
T2 - 33rd Conference on Uncertainty in Artificial Intelligence, UAI 2017
Y2 - 11 August 2017 through 15 August 2017
ER -