How does Naïve Bayes scale in distributed machine learning systems?

Naïve Bayes scales efficiently in distributed systems because it requires only aggregated sufficient statistics.

Naïve Bayes is inherently parallelizable because training requires only counting feature occurrences per class. In distributed systems, partial counts can be computed independently and merged using reduce operations. This makes it ideal for large-scale systems like Spark-based NLP pipelines.