A5071086616- Bayesian Modeling and Causal Inference
- Multi-Criteria Decision Making
- AI-based Problem Solving and Planning
- Data Mining Algorithms and Applications
- Domain Adaptation and Few-Shot Learning
- Machine Learning and Algorithms
Northwestern Polytechnical University
2020-2023
How to improve the efficiency of exact learning Bayesian network structure is a challenging issue. In this paper, four different causal constraints algorithms are added into score calculations prune possible parent sets, improving state-of-the-art algorithms' efficiency. Experimental results indicate that can significantly with only slight loss accuracy. Under constraints, these about 70% sets and reduce 60% running time while losing no more than 2% accuracy on average. Additionally,...
Learning the structure of a Bayesian network and considering efficiency accuracy learning has always been hot topic for researchers. This paper proposes two constraints to solve problem that A* algorithm, an exact is not efficient enough search larger networks. On one hand, parent–child set reduce number potential optimal parent sets. other path are obtained from sets constrain process algorithm. Both proposed based on Experiments show time algorithm can be significantly improved, ability...
Exact algorithms for learning optimal Bayesian networks require much more time and are used in small networks. This paper adds ancestral partition constraints into the bidirectional heuristic search algorithm based on order graph. The can be obtained by extracting strongly connected components from possible parent sets. Experiments show that significantly improve efficiency scalability of search. In addition, with constraints, has better larger than state-of-the-art algorithms.