Enhance learning efficiency of oblique decision tree via feature concatenation

Oblique Decision Tree (ODT) partitions the feature space using linear combinations of features, in contrast to a conventional Decision Tree (DT) which is restricted to axis-parallel splits. ODT has been proven to have a stronger representation ability than DT, as it provides a way to create shallower tree structures while still approximating complex decision boundaries. However, its learning efficiency is still insufficient, since the linear projections cannot be transmitted to the child nodes, resulting in a waste of model parameters. In this work, we propose an enhanced ODT method with Feature Concatenation (FC-ODT), which enables in-model feature transformation to transmit the projections along the decision paths. Theoretically, we prove that our method enjoys a faster consistency rate w.r.t. the tree depth, indicating that our method possesses a significant advantage in generalization performance, especially for shallow trees. Experiments show that FC-ODT outperforms the other decision trees with a limited tree depth. © 2025 Elsevier Inc.