An efficient approach for multiple probabilistic inferences with Deepwalk based Bayesian network embedding
作者：
Highlights：
• Construct the WDG to represent the states with transition probabilities in BN.
• Propose the method for BN embedding to facilitate probabilistic inferences.
• Provide a method to approximate the probabilities based on BN embeddings.
• Propose an efficient algorithm for multiple probabilistic inferences.
• Outperform other state-of-the-art competitors on efficiency with orders of magnitude.
摘要
•Construct the WDG to represent the states with transition probabilities in BN.•Propose the method for BN embedding to facilitate probabilistic inferences.•Provide a method to approximate the probabilities based on BN embeddings.•Propose an efficient algorithm for multiple probabilistic inferences.•Outperform other state-of-the-art competitors on efficiency with orders of magnitude.
论文关键词：Bayesian network,Probabilistic inference,Network embedding,Random walk
论文评审过程：Received 6 February 2021, Revised 16 December 2021, Accepted 17 December 2021, Available online 24 December 2021, Version of Record 6 January 2022.
论文官网地址：https://doi.org/10.1016/j.knosys.2021.107996
