标题： 分支网络：一种用于结构化多类分类的神经符号学习框架 显示英文标题

标题： BranchNet: A Neuro-Symbolic Learning Framework for Structured Multi-Class Classification

摘要： 我们引入了BranchNet，这是一种神经符号学习框架，它将决策树集成转换为稀疏的、部分连接的神经网络。 每个分支被定义为从根到叶节点父节点的决策路径，被映射到一个隐藏神经元，保留符号结构的同时实现基于梯度的优化。 生成的模型紧凑、可解释，并且不需要手动调整架构。 在一系列结构化的多类分类基准测试中，BranchNet在准确性方面始终优于XGBoost，且差异具有统计显著性。 我们详细介绍了架构、训练过程和稀疏性动态，并讨论了模型在符号可解释性方面的优势以及当前的局限性，特别是在二元任务中，进一步的自适应校准可能有益。 显示英文摘要

摘要： We introduce BranchNet, a neuro-symbolic learning framework that transforms decision tree ensembles into sparse, partially connected neural networks. Each branch, defined as a decision path from root to a parent of leaves, is mapped to a hidden neuron, preserving symbolic structure while enabling gradient-based optimization. The resulting models are compact, interpretable, and require no manual architecture tuning. Evaluated on a suite of structured multi-class classification benchmarks, BranchNet consistently outperforms XGBoost in accuracy, with statistically significant gains. We detail the architecture, training procedure, and sparsity dynamics, and discuss the model's strengths in symbolic interpretability as well as its current limitations, particularly on binary tasks where further adaptive calibration may be beneficial.