NADT: Neighborhood-Augmented Neural Decision Trees

Neural decision trees enable end-to-end gradient optimization of hierarchical routing. Their split functions are globally fixed during inference, applying identical decision boundaries irrespective of local data structure. Meanwhile, $k$ -nearest neighbor methods provide sample-adaptive local awareness, but their flat architectures cannot decompose complex boundaries hierarchically. To address this limitation, we propose NADT, which equips a neural decision tree with neighborhood-adaptive routing through a Neighborhood Context Module (NCM) and a soft decision tree ensemble. NCM maintains $M$ learnable prototypes in a shared embedding space and maps sample-to-prototype distances via temperature-scaled Softmax to node-level biases. These biases are injected into the oblique split nodes of the soft tree ensemble, shifting decision boundaries dynamically with each sample's neighborhood context. Since prototypes are learned parameters, NADT achieves local awareness without retrieving the training set at inference. Extensive experiments on 30 public datasets demonstrate that NADT outperforms 11 competing methods, with ablation confirming module effectiveness and visualization validating the interpretability.