A Comprehensively Improved Hybrid Algorithm for Learning Bayesian Networks: Multiple Compound Memory Erasing
This work addresses a domain-specific problem for researchers and practitioners in machine learning and statistics who need efficient and accurate Bayesian network learning, but it appears incremental as it builds on and combines existing constraint-based and score-based methods.
The paper tackles the inefficiency and inaccuracy of existing Bayesian network learning algorithms by proposing a new hybrid algorithm called MCME, which shows better or similar performance in experiments compared to some existing methods.
Using a Bayesian network to analyze the causal relationship between nodes is a hot spot. The existing network learning algorithms are mainly constraint-based and score-based network generation methods. The constraint-based method is mainly the application of conditional independence (CI) tests, but the inaccuracy of CI tests in the case of high dimensionality and small samples has always been a problem for the constraint-based method. The score-based method uses the scoring function and search strategy to find the optimal candidate network structure, but the search space increases too much with the increase of the number of nodes, and the learning efficiency is very low. This paper presents a new hybrid algorithm, MCME (multiple compound memory erasing). This method retains the advantages of the first two methods, solves the shortcomings of the above CI tests, and makes innovations in the scoring function in the direction discrimination stage. A large number of experiments show that MCME has better or similar performance than some existing algorithms.