Dynamic Connected Neural Decision Classifier and Regressor with Dynamic Softing Pruning

TL;DR

This paper introduces a self-adaptive model combining Dynamic Connected Neural Decision Networks with Dynamic Soft Pruning, enhancing classification robustness and reducing overfitting across diverse datasets.

Contribution

It proposes a novel end-to-end training approach for neural decision forests and a dynamic soft pruning method to improve model adaptability and efficiency.

Findings

Higher robustness over different data distributions

No performance loss with pruning, better than unpruned models

Outperforms popular algorithms in classification tasks

Abstract

To deal with various datasets over different complexity, this paper presents an self-adaptive learning model that combines the proposed Dynamic Connected Neural Decision Networks (DNDN) and a new pruning method--Dynamic Soft Pruning (DSP). DNDN is a combination of random forests and deep neural networks that enjoys both the advantages of strong classification capability of tree-like structure and representation learning capability of network structure. Based on Deep Neural Decision Forests (DNDF), this paper adopts an end-to-end training approach by representing the classification distribution with multiple randomly initialized softmax layers, which further allows an ensemble of multiple random forests attached to layers of neural network with different depth. We also propose a soft pruning method DSP to reduce the redundant connections of the network adaptively to avoid over-fitting simple dataset. The model demonstrates no performance loss compared with unpruned models and even higher robustness over different data and feature distribution. Extensive experiments on different datasets demonstrate the superiority of the proposed model over other popular algorithms in solving classification tasks.