InTreeger: An End-to-End Framework for Integer-Only Decision Tree Inference

TL;DR

InTreeger is a comprehensive framework that converts decision trees into highly optimized integer-only C code, enabling efficient, precise, and hardware-agnostic inference on resource-limited devices.

Contribution

It introduces an end-to-end, architecture-agnostic method for generating integer-only decision tree implementations without loss of accuracy.

Findings

Significant reduction in inference latency across ARM, x86, RISC-V architectures.

Improved energy efficiency over floating-point decision tree implementations.

Enables deployment on ultra-low power and embedded systems.

Abstract

Integer quantization has emerged as a critical technique to facilitate deployment on resource-constrained devices. Although they do reduce the complexity of the learning models, their inference performance is often prone to quantization-induced errors. To this end, we introduce InTreeger: an end-to-end framework that takes a training dataset as input, and outputs an architecture-agnostic integer-only C implementation of tree-based machine learning model, without loss of precision. This framework enables anyone, even those without prior experience in machine learning, to generate a highly optimized integer-only classification model that can run on any hardware simply by providing an input dataset and target variable. We evaluated our generated implementations across three different architectures (ARM, x86, and RISC-V), resulting in significant improvements in inference latency. In addition, we show the energy efficiency compared to typical decision tree implementations that rely on floating-point arithmetic. The results underscore the advantages of integer-only inference, making it particularly suitable for energy- and area-constrained devices such as embedded systems and edge computing platforms, while also enabling the execution of decision trees on existing ultra-low power devices.