Oblique Decision Trees from Derivatives of ReLU Networks

30 Sep 2019  ·  Guang-He Lee, Tommi S. Jaakkola ·

We show how neural models can be used to realize piece-wise constant functions such as decision trees. The proposed architecture, which we call locally constant networks, builds on ReLU networks that are piece-wise linear and hence their associated gradients with respect to the inputs are locally constant. We formally establish the equivalence between the classes of locally constant networks and decision trees. Moreover, we highlight several advantageous properties of locally constant networks, including how they realize decision trees with parameter sharing across branching / leaves. Indeed, only $M$ neurons suffice to implicitly model an oblique decision tree with $2^M$ leaf nodes. The neural representation also enables us to adopt many tools developed for deep networks (e.g., DropConnect (Wan et al., 2013)) while implicitly training decision trees. We demonstrate that our method outperforms alternative techniques for training oblique decision trees in the context of molecular property classification and regression tasks.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Drug Discovery BACE Ensemble locally constant network AUC 0.874 # 2
Drug Discovery PDBbind Ensemble locally constant networks RMSE 1.219 # 1
Drug Discovery SIDER Ensemble locally constant networks AUC 0.685 # 1