Enhancing Neural Network Interpretability Through Conductance-Based Information Plane Analysis

TL;DR

This paper introduces a conductance-based method to analyze neural network information flow, providing more precise insights into layer contributions and challenging existing theories, thereby enhancing interpretability and robustness.

Contribution

It proposes a novel conductance-based Information Plane analysis and ITE metric, improving understanding of information dynamics and feature attribution in neural networks.

Findings

Identifies critical layers influencing performance and interpretability

Reveals complex information compression and utilization patterns

Challenges predictions of the Information Bottleneck theory

Abstract

The Information Plane is a conceptual framework used to analyze the flow of information in neural networks, but traditional methods based on activations may not fully capture the dynamics of information processing. This paper introduces a new approach that uses layer conductance, a measure of sensitivity to input features, to enhance the Information Plane analysis. By incorporating gradient-based contributions, we provide a more precise characterization of information dynamics within the network. The proposed conductance-based Information Plane and a new Information Transformation Efficiency (ITE) metric are evaluated on pretrained ResNet50 and VGG16 models using the ImageNet dataset. Our results demonstrate the ability to identify critical hidden layers that contribute significantly to model performance and interpretability, giving insights into information compression, preservation, and utilization across layers. The conductance-based approach offers a granular perspective on feature attribution, enhancing our understanding of the decision-making processes within neural networks. Furthermore, our empirical findings challenge certain theoretical predictions of the Information Bottleneck theory, highlighting the complexities of information dynamics in real-world data scenarios. The proposed method not only advances our understanding of information dynamics in neural networks but also has the potential to significantly impact the broader field of Artificial Intelligence by enabling the development of more interpretable, efficient, and robust models.