Relational Learning with One Network: An Asymptotic Analysis

Rongjing Xiang, Jennifer Neville
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, PMLR 15:779-788, 2011.

Abstract

Theoretical analysis of structured learning methods has focused primarily on domains where the data consist of independent (albeit structured) examples. Although the statistical relational learning (SRL) community has recently developed many classification methods for graph and network domains, much of this work has focused on modeling domains where there is a single network for learning. For example, we could learn a model to predict the political views of users in an online social network, based on the friendship relationships among users. In this example, the data would be drawn from a single large network (e.g., Facebook) and increasing the data size would correspond to acquiring a larger graph. Although SRL methods can successfully improve classification in these types of domains, there has been little theoretical analysis of addressing the issue of single network domains. In particular, the asymptotic properties of estimation are not clear if the size of the model grows with the size of the network. In this work, we focus on outlining the conditions under which learning from a single network will be asymptotically consistent and normal. Moreover, we compare the properties of maximum likelihood estimation (MLE) with that of generalized maximum pseudolikelihood estimation (MPLE) and use the resulting understanding to propose novel MPLE estimators for single network domains. We include empirical analysis on both synthetic and real network data to illustrate the findings. [pdf]

Cite this Paper


BibTeX
@InProceedings{pmlr-v15-xiang11a, title = {Relational Learning with One Network: An Asymptotic Analysis}, author = {Xiang, Rongjing and Neville, Jennifer}, booktitle = {Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics}, pages = {779--788}, year = {2011}, editor = {Gordon, Geoffrey and Dunson, David and Dudík, Miroslav}, volume = {15}, series = {Proceedings of Machine Learning Research}, address = {Fort Lauderdale, FL, USA}, month = {11--13 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v15/xiang11a/xiang11a.pdf}, url = {https://proceedings.mlr.press/v15/xiang11a.html}, abstract = {Theoretical analysis of structured learning methods has focused primarily on domains where the data consist of independent (albeit structured) examples. Although the statistical relational learning (SRL) community has recently developed many classification methods for graph and network domains, much of this work has focused on modeling domains where there is a single network for learning. For example, we could learn a model to predict the political views of users in an online social network, based on the friendship relationships among users. In this example, the data would be drawn from a single large network (e.g., Facebook) and increasing the data size would correspond to acquiring a larger graph. Although SRL methods can successfully improve classification in these types of domains, there has been little theoretical analysis of addressing the issue of single network domains. In particular, the asymptotic properties of estimation are not clear if the size of the model grows with the size of the network. In this work, we focus on outlining the conditions under which learning from a single network will be asymptotically consistent and normal. Moreover, we compare the properties of maximum likelihood estimation (MLE) with that of generalized maximum pseudolikelihood estimation (MPLE) and use the resulting understanding to propose novel MPLE estimators for single network domains. We include empirical analysis on both synthetic and real network data to illustrate the findings. [pdf]} }
Endnote
%0 Conference Paper %T Relational Learning with One Network: An Asymptotic Analysis %A Rongjing Xiang %A Jennifer Neville %B Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2011 %E Geoffrey Gordon %E David Dunson %E Miroslav Dudík %F pmlr-v15-xiang11a %I PMLR %P 779--788 %U https://proceedings.mlr.press/v15/xiang11a.html %V 15 %X Theoretical analysis of structured learning methods has focused primarily on domains where the data consist of independent (albeit structured) examples. Although the statistical relational learning (SRL) community has recently developed many classification methods for graph and network domains, much of this work has focused on modeling domains where there is a single network for learning. For example, we could learn a model to predict the political views of users in an online social network, based on the friendship relationships among users. In this example, the data would be drawn from a single large network (e.g., Facebook) and increasing the data size would correspond to acquiring a larger graph. Although SRL methods can successfully improve classification in these types of domains, there has been little theoretical analysis of addressing the issue of single network domains. In particular, the asymptotic properties of estimation are not clear if the size of the model grows with the size of the network. In this work, we focus on outlining the conditions under which learning from a single network will be asymptotically consistent and normal. Moreover, we compare the properties of maximum likelihood estimation (MLE) with that of generalized maximum pseudolikelihood estimation (MPLE) and use the resulting understanding to propose novel MPLE estimators for single network domains. We include empirical analysis on both synthetic and real network data to illustrate the findings. [pdf]
RIS
TY - CPAPER TI - Relational Learning with One Network: An Asymptotic Analysis AU - Rongjing Xiang AU - Jennifer Neville BT - Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics DA - 2011/06/14 ED - Geoffrey Gordon ED - David Dunson ED - Miroslav Dudík ID - pmlr-v15-xiang11a PB - PMLR DP - Proceedings of Machine Learning Research VL - 15 SP - 779 EP - 788 L1 - http://proceedings.mlr.press/v15/xiang11a/xiang11a.pdf UR - https://proceedings.mlr.press/v15/xiang11a.html AB - Theoretical analysis of structured learning methods has focused primarily on domains where the data consist of independent (albeit structured) examples. Although the statistical relational learning (SRL) community has recently developed many classification methods for graph and network domains, much of this work has focused on modeling domains where there is a single network for learning. For example, we could learn a model to predict the political views of users in an online social network, based on the friendship relationships among users. In this example, the data would be drawn from a single large network (e.g., Facebook) and increasing the data size would correspond to acquiring a larger graph. Although SRL methods can successfully improve classification in these types of domains, there has been little theoretical analysis of addressing the issue of single network domains. In particular, the asymptotic properties of estimation are not clear if the size of the model grows with the size of the network. In this work, we focus on outlining the conditions under which learning from a single network will be asymptotically consistent and normal. Moreover, we compare the properties of maximum likelihood estimation (MLE) with that of generalized maximum pseudolikelihood estimation (MPLE) and use the resulting understanding to propose novel MPLE estimators for single network domains. We include empirical analysis on both synthetic and real network data to illustrate the findings. [pdf] ER -
APA
Xiang, R. & Neville, J.. (2011). Relational Learning with One Network: An Asymptotic Analysis. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 15:779-788 Available from https://proceedings.mlr.press/v15/xiang11a.html.

Related Material