How does Naïve Bayes relate to probabilistic graphical model inference complexity?

Naïve Bayes achieves O(n) inference complexity due to conditional independence structure in its graphical model.

In general Bayesian networks, inference can be exponential in number of variables. Naïve Bayes simplifies this by enforcing a star-shaped graph, allowing factorization into independent likelihood terms. This reduces inference complexity from exponential to linear in feature count.