A Comparison of Decision Forest Inference Platforms from A Database Perspective

TL;DR

This paper compares various decision forest inference platforms, including in-database solutions, to evaluate their performance and identify optimal use cases, revealing that in-database inference can significantly outperform external frameworks in specific scenarios.

Contribution

The study provides a comprehensive performance comparison of multiple decision forest inference frameworks and introduces an in-database inference framework, netsDB, with novel optimizations.

Findings

netsDB excels with small models on large datasets and all models on small datasets.

Relation-centric representation boosts large-scale model performance.

Model reuse optimization enhances small-scale dataset performance.

Abstract

Decision forest, including RandomForest, XGBoost, and LightGBM, is one of the most popular machine learning techniques used in many industrial scenarios, such as credit card fraud detection, ranking, and business intelligence. Because the inference process is usually performance-critical, a number of frameworks were developed and dedicated for decision forest inference, such as ONNX, TreeLite from Amazon, TensorFlow Decision Forest from Google, HummingBird from Microsoft, Nvidia FIL, and lleaves. However, these frameworks are all decoupled with data management frameworks. It is unclear whether in-database inference will improve the overall performance. In addition, these frameworks used different algorithms, optimization techniques, and parallelism models. It is unclear how these implementations will affect the overall performance and how to make design decisions for an in-database inference framework. In this work, we investigated the above questions by comprehensively comparing the end-to-end performance of the aforementioned inference frameworks and netsDB, an in-database inference framework we implemented. Through this study, we identified that netsDB is best suited for handling small-scale models on large-scale datasets and all-scale models on small-scale datasets, for which it achieved up to hundreds of times of speedup. In addition, the relation-centric representation we proposed significantly improved netsDB's performance in handling large-scale models, while the model reuse optimization we proposed further improved netsDB's performance in handling small-scale datasets.