Fast Committee-Based Structure Learning

Ernest Mwebaze, John A. Quinn
Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008, PMLR 6:203-214, 2010.

Abstract

Current methods for causal structure learning tend to be computationally intensive or intractable for large datasets. Some recent approaches have speeded up the process by first making hard decisions about the set of parents and children for each variable, in order to break large-scale problems into sets of tractable local neighbourhoods. We use this principle in order to apply a structure learning committee for orientating edges between variables. We find that a combination of weak structure learners can be effective in recovering causal dependencies. Though such a formulation would be intractable for large problems at the global level, we show that it can run quickly when processing local neighbourhoods in turn. Experimental results show that this localized, committee-based approach has advantages over standard causal discovery algorithms both in terms of speed and accuracy.

Cite this Paper


BibTeX
@InProceedings{pmlr-v6-mwebaze10a, title = {Fast Committee-Based Structure Learning}, author = {Mwebaze, Ernest and Quinn, John A.}, booktitle = {Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008}, pages = {203--214}, year = {2010}, editor = {Guyon, Isabelle and Janzing, Dominik and Schölkopf, Bernhard}, volume = {6}, series = {Proceedings of Machine Learning Research}, address = {Whistler, Canada}, month = {12 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v6/mwebaze10a/mwebaze10a.pdf}, url = {https://proceedings.mlr.press/v6/mwebaze10a.html}, abstract = {Current methods for causal structure learning tend to be computationally intensive or intractable for large datasets. Some recent approaches have speeded up the process by first making hard decisions about the set of parents and children for each variable, in order to break large-scale problems into sets of tractable local neighbourhoods. We use this principle in order to apply a structure learning committee for orientating edges between variables. We find that a combination of weak structure learners can be effective in recovering causal dependencies. Though such a formulation would be intractable for large problems at the global level, we show that it can run quickly when processing local neighbourhoods in turn. Experimental results show that this localized, committee-based approach has advantages over standard causal discovery algorithms both in terms of speed and accuracy.} }
Endnote
%0 Conference Paper %T Fast Committee-Based Structure Learning %A Ernest Mwebaze %A John A. Quinn %B Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008 %C Proceedings of Machine Learning Research %D 2010 %E Isabelle Guyon %E Dominik Janzing %E Bernhard Schölkopf %F pmlr-v6-mwebaze10a %I PMLR %P 203--214 %U https://proceedings.mlr.press/v6/mwebaze10a.html %V 6 %X Current methods for causal structure learning tend to be computationally intensive or intractable for large datasets. Some recent approaches have speeded up the process by first making hard decisions about the set of parents and children for each variable, in order to break large-scale problems into sets of tractable local neighbourhoods. We use this principle in order to apply a structure learning committee for orientating edges between variables. We find that a combination of weak structure learners can be effective in recovering causal dependencies. Though such a formulation would be intractable for large problems at the global level, we show that it can run quickly when processing local neighbourhoods in turn. Experimental results show that this localized, committee-based approach has advantages over standard causal discovery algorithms both in terms of speed and accuracy.
RIS
TY - CPAPER TI - Fast Committee-Based Structure Learning AU - Ernest Mwebaze AU - John A. Quinn BT - Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008 DA - 2010/02/18 ED - Isabelle Guyon ED - Dominik Janzing ED - Bernhard Schölkopf ID - pmlr-v6-mwebaze10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 6 SP - 203 EP - 214 L1 - http://proceedings.mlr.press/v6/mwebaze10a/mwebaze10a.pdf UR - https://proceedings.mlr.press/v6/mwebaze10a.html AB - Current methods for causal structure learning tend to be computationally intensive or intractable for large datasets. Some recent approaches have speeded up the process by first making hard decisions about the set of parents and children for each variable, in order to break large-scale problems into sets of tractable local neighbourhoods. We use this principle in order to apply a structure learning committee for orientating edges between variables. We find that a combination of weak structure learners can be effective in recovering causal dependencies. Though such a formulation would be intractable for large problems at the global level, we show that it can run quickly when processing local neighbourhoods in turn. Experimental results show that this localized, committee-based approach has advantages over standard causal discovery algorithms both in terms of speed and accuracy. ER -
APA
Mwebaze, E. & Quinn, J.A.. (2010). Fast Committee-Based Structure Learning. Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008, in Proceedings of Machine Learning Research 6:203-214 Available from https://proceedings.mlr.press/v6/mwebaze10a.html.

Related Material