提出细粒度量化方法，让决策树模型更省资源且保持高精度。
FQTree: Fine-grained Quantization and Hardware Generation of Boosted Decision Trees
- 设计可硬件优化的叶子值量化方案，支持紧凑整数表示和剪枝控制
- 在提升过程中动态适应量化误差，使模型在低延迟硬件上部署更高效
- 适合需要低延迟、高能效的嵌入式决策树应用
提升型决策树（BDTs）广泛应用于对延迟敏感的场景，但其高效硬件部署仍具挑战。现有设计多依赖均匀或人工调优的定点格式，易导致硬件开销过大或精度损失。本文提出FQTree算法，实现面向硬件的细粒度量化感知训练，并构建QXGB框架完成自动化硬件生成。FQTree引入一种面向硬件的叶子值量化机制，采用全局量化步长与树级偏移，实现紧凑的非负整数叶子表示，支持可控截断/剪枝及偏置折叠，降低数据通路成本。该量化方法在提升过程中被持续应用，使后续树能适应已量化集成的误差，再通过编译器流程转化为低延迟硬件实现。在JSC、MNIST和NID数据集上的实验表明，相比当前最先进的基于FPGA的BDT设计，本方法可减少26%-57%的查找表（LUT）用量，同时保持或提升准确率。
原文摘要 · Abstract (English)
Boosted decision trees (BDTs) are widely used in latency-critical applications, but efficient hardware deployment remains challenging. Existing designs often rely on uniform or manually tuned fixed-point formats, which can introduce unnecessary hardware cost or accuracy loss. This work presents the FQTree algorithm{https://github.com/ecs-bristol/FQTree} for fine-grained quantization-aware training of BDTs, together with the QXGB framework for automatic hardware generation. FQTree introduces a hardware-oriented leaf-value quantization scheme that uses a global quantization step together with a tree-wise shift, enabling compact non-negative integer leaf representations, controlled clipping/pruning, and bias folding to reduce datapath cost. This work further applies this quantization during boosting so that later trees adapt to the errors of the already-quantized ensemble, and then lowers the trained model into low-latency hardware implementations through a compiler-based flow. Results on JSC, MNIST, and NID show that our method reduces LUT usage by 26-57\% compared with the state-of-the-art FPGA-based BDT designs while matching or improving accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。