• Corpus ID: 1930258

Algorithms for Large Scale Markov Blanket Discovery

@inproceedings{Tsamardinos2003AlgorithmsFL,
  title={Algorithms for Large Scale Markov Blanket Discovery},
  author={I. Tsamardinos and Constantin F. Aliferis and Alexander R. Statnikov},
  booktitle={FLAIRS Conference},
  year={2003}
}
This paper presents a number of new algorithms for discovering the Markov Blanket of a target variable T from training data. [] Key Method We introduce a low-order polynomial algorithm and several variants that soundly induce the Markov Blanket under certain broad conditions in datasets with thousands of variables and compare them to other state-of-the-art local and global methods with excellent results.

Figures from this paper

Fast Markov blanket discovery

TLDR
A novel algorithm called FAST-IAMB for the induction of Markov blankets that employs a fast heuristic to quickly converge to the Markov blanket and shows that it performs reasonably faster than existing algorithms.

Speculative Markov blanket discovery for optimal feature selection

TLDR
A novel algorithm for the induction of Markov blankets from data, called Fast-IAMB, that employs a heuristic to quickly recover the Markov blanket and performs in many cases faster and more reliably than existing algorithms without adversely affecting the accuracy of the recovered Markov covers.

Markov Blanket Discovery using Minimum Message Length

TLDR
This work develops and explores three new methods of MB discovery using Minimum Message Length (MML) and compares them empirically to the best existing methods, whether developed specifically as MB discovery or as feature selection.

An Improved IAMB Algorithm for Markov Blanket Discovery

TLDR
Experimental results show that λ -IAMB algorithm performs better than IAMB by finding Markov blanket of variables in typical Bayesian network and by testing the performance of them as feature selection method on some well-known real world datasets.

Dynamic Ordering-Based Search Algorithm for Markov Blanket Discovery

TLDR
The Dynamic Ordering-based Search algorithm (DOS) for learning a Markov blanket of a domain variable from statistical conditional independence tests on data is proposed and empirically compare it with the state-of-the-art algorithm.

Tradeoff Analysis of Different Markov Blanket Local Learning Approaches

TLDR
Those known published algorithms, including KS, GS, IAMB and its variants, PCMB, and one newly proposed called BFMB are compared with the theoretical basis and practical values of each to help applicants to determine which ones to take in their specific scenarios.

Learning Markov Blankets for Continuous or Discrete Networks via Feature Selection

TLDR
An argument that ensemble masking measures can provide an approximate Markov Blanket is presented and an ensemble feature selection method can be used to learnMarkov Blankets for either discrete or continuous networks (without linear, Gaussian assumptions).

A Fast Markov blanket discovery algorithm

  • Xiaofeng ZhuYoulong Yang
  • Computer Science
    2014 IEEE 5th International Conference on Software Engineering and Service Science
  • 2014
TLDR
An efficient and effective algorithm, called Fast Iterative Parent-Child based search of MB (FIPC-MB) is proposed to learn the MB of the target variable T by combining the IPC-MB algorithm with mutual information knowledge to initialize candidate parents and children of the the target node.

Local Causal and Markov Blanket Induction for Causal Discovery and Feature Selection for Classification Part I: Algorithms and Empirical Evaluation

TLDR
It is found that non-causal feature selection methods cannot be interpreted causally even when they achieve excellent predictivity, so only local causal techniques should be used when insight into causal structure is sought.

Identifying Markov blankets with decision tree induction

TLDR
A modest variation of an inexpensive, accurate, off-the-shelf induction engine mitigates the need for specialized procedures, and establishes baseline performance against which specialized algorithms can be compared.
...

References

SHOWING 1-10 OF 10 REFERENCES

Bayesian Network Induction via Local Neighborhoods

TLDR
This work presents an efficient algorithm for learning Bayes networks from data by first identifying each node's Markov blankets, then connecting nodes in a maximally consistent way, and proves that under mild assumptions, the approach requires time polynomial in the size of the data and the number of nodes.

Learning Bayesian Networks from Data: An Efficient Approach Based on Information Theory

TLDR
This paper addresses the problem of learning Bayesian network structures from data by using an information theoretic dependency analysis approach and the empirical results show that the approach is efficient and reliable.

Toward Optimal Feature Selection

TLDR
An efficient algorithm for feature selection which computes an approximation to the optimal feature selection criterion is given, showing that the algorithm effectively handles datasets with a very large number of features.

Strong completeness and faithfulness in Bayesian networks

TLDR
It is shown that in a strong measure-theoretic sense almost all discrete distributions for a given network structure are faithful; i.e. the independence facts true of the distribution are all and only those entailed by the network structure.

The ALARM Monitoring System: A Case Study with two Probabilistic Inference Techniques for Belief Networks

TLDR
Two algorithms were applied to this belief network: a message-passing algorithm by Pearl for probability updating in multiply connected networks using the method of conditioning and the Lauritzen-Spiegelhalter algorithm for local probability computations on graphical structures.

Probabilistic reasoning in expert systems - theory and algorithms

TLDR
This text is a reprint of the seminal 1989 book Probabilistic Reasoning in Expert systems: Theory and Algorithms, which helped serve to create the field the authors now call Bayesian networks and provides an insightful comparison of the two most prominent approaches to probability.

Constructing Bayesian Network Models of Gene Expression Networks from Microarray Data

TLDR
Current techniques that are available for searching for the causal relations between variables are reviewed, algorithmic and data gathering obstacles to applying these techniques to gene expression levels are described, and the prospects for overcoming these obstacles are described.

Basic principles of ROC analysis.

  • C. Metz
  • Medicine
    Seminars in nuclear medicine
  • 1978

Towards Principled Feature Selection: Relevancy, Filters and Wrappers