Not All Features Are Equal: Feature Leveling Deep Neural Networks for Better Interpretation

TL;DR

This paper introduces a feature leveling architecture for deep neural networks that isolates features at different levels to enhance interpretability without sacrificing performance.

Contribution

The paper proposes a novel feature leveling architecture that separates low and high level features per layer to improve interpretability of DNNs.

Findings

Achieves competitive accuracy on standard datasets

Enhances model interpretability through feature separation

Publicly available implementation for reproducibility

Abstract

Self-explaining models are models that reveal decision making parameters in an interpretable manner so that the model reasoning process can be directly understood by human beings. General Linear Models (GLMs) are self-explaining because the model weights directly show how each feature contributes to the output value. However, deep neural networks (DNNs) are in general not self-explaining due to the non-linearity of the activation functions, complex architectures, obscure feature extraction and transformation process. In this work, we illustrate the fact that existing deep architectures are hard to interpret because each hidden layer carries a mix of low level features and high level features. As a solution, we propose a novel feature leveling architecture that isolates low level features from high level features on a per-layer basis to better utilize the GLM layer in the proposed architecture for interpretation. Experimental results show that our modified models are able to achieve competitive results comparing to main-stream architectures on standard datasets while being more self-explainable. Our implementations and configurations are publicly available for reproductions