[SPARK-3383] DecisionTree aggregate size could be smaller

• Type: Improvement
• Status: Resolved
• Priority: Minor
• Resolution: Incomplete
• Affects Version/s: 1.1.0
• Component/s: MLlib
• Labels: bulk-closed
• Assignee: Unassigned
• Reporter: Joseph K. Bradley
• Created: 03/Sep/14 18:53
• Updated: 21/May/19 04:15
• Resolved: 21/May/19 04:15

Description

Storage and communication optimization:
DecisionTree aggregate statistics could store less data (described below). The savings would be significant for datasets with many low-arity categorical features (binary features, or unordered categorical features). Savings would be negligible for continuous features.

DecisionTree stores a vector sufficient statistics for each (node, feature, bin). We could store 1 fewer bin per (node, feature): For a given (node, feature), if we store these vectors for all but the last bin, and also store the total statistics for each node, then we could compute the statistics for the last bin. For binary and unordered categorical features, this would cut in half the number of bins to store and communicate.

Issue Links

• Is contained by: SPARK-14045 DecisionTree improvement umbrella
• is related to: SPARK-14351 Optimize ImpurityAggregator for decision trees
• is related to: SPARK-22451 Reduce decision tree aggregate size for unordered features from O(2^numCategories) to O(numCategories)
• relates to: SPARK-10788 Decision Tree duplicates bins for unordered categorical features