A novel algorithm for scalable and accurate Bayesian network learning.

@article{citeulike:1325512, abstract = {Bayesian Networks (BN) is a knowledge representation formalism that has been proven to be valuable in biomedicine for constructing decision support systems and for generating causal hypotheses from data. Given the emergence of datasets in medicine and biology with thousands of variables and that current algorithms do not scale more than a few hundred variables in practical domains, new efficient and accurate algorithms are needed to learn high quality BNs from data. We present a new algorithm called Max-Min Hill-Climbing (MMHC) that builds upon and improves the Sparse Candidate (SC) algorithm; a state-of-the-art algorithm that scales up to datasets involving hundreds of variables provided the generating networks are sparse. Compared to the SC, on a number of datasets from medicine and biology, (a) MMHC discovers BNs that are structurally closer to the data-generating BN, (b) the discovered networks are more probable given the data, (c) MMHC is computationally more efficient and scalable than SC, and (d) the generating networks are not required to be uniformly sparse nor is the user of MMHC required to guess correctly the network connectivity}, address = {Discoivery Systems Laboratory, Department of Biomedical Informatics, Vanderbilt University, 2209 Garland Avenue, Nashville, TN 37232, USA. laura.e.brown@vanderbilt.edu}, author = {Brown, L. E. and Tsamardinos, I. and Aliferis, C. F. }, citeulike-article-id = {1325512}, journal = {Medinfo}, keywords = {bayesian\_network, graphical\_models, machine\_learning, structure\_learning}, number = {Pt 1}, pages = {711--715}, posted-at = {2007-09-06 10:26:16}, priority = {0}, title = {A novel algorithm for scalable and accurate Bayesian network learning.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/15360905}, volume = {11}, year = {2004} }

TY - JOUR ID - citeulike:1325512 L3 - citeulike-article-id:1325512 TI - A novel algorithm for scalable and accurate Bayesian network learning. JF - Medinfo VL - 11 IS - Pt 1 SP - 711 EP - 715 AD - Discoivery Systems Laboratory, Department of Biomedical Informatics, Vanderbilt University, 2209 Garland Avenue, Nashville, TN 37232, USA. laura.e.brown@vanderbilt.edu N2 - Bayesian Networks (BN) is a knowledge representation formalism that has been proven to be valuable in biomedicine for constructing decision support systems and for generating causal hypotheses from data. Given the emergence of datasets in medicine and biology with thousands of variables and that current algorithms do not scale more than a few hundred variables in practical domains, new efficient and accurate algorithms are needed to learn high quality BNs from data. We present a new algorithm called Max-Min Hill-Climbing (MMHC) that builds upon and improves the Sparse Candidate (SC) algorithm; a state-of-the-art algorithm that scales up to datasets involving hundreds of variables provided the generating networks are sparse. Compared to the SC, on a number of datasets from medicine and biology, (a) MMHC discovers BNs that are structurally closer to the data-generating BN, (b) the discovered networks are more probable given the data, (c) MMHC is computationally more efficient and scalable than SC, and (d) the generating networks are not required to be uniformly sparse nor is the user of MMHC required to guess correctly the network connectivity KW - bayesian_network KW - graphical_models KW - machine_learning KW - structure_learning AU - Brown, LE AU - Tsamardinos, I AU - Aliferis, CF PY - 2004/// UR - http://view.ncbi.nlm.nih.gov/pubmed/15360905 ER -