NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions
This work addresses the problem of neural network interpretability for researchers and practitioners, offering a novel approach that is incremental in advancing explainability methods.
The paper tackles the challenge of interpreting neural networks by shifting focus from individual neurons to groups of neurons, proposing the NeurFlow framework that identifies core neurons and clusters them based on functional interactions to improve interpretability and reduce computational costs, with empirical validation and applications in image debugging and concept labeling.
Understanding the inner workings of neural networks is essential for enhancing model performance and interpretability. Current research predominantly focuses on examining the connection between individual neurons and the model's final predictions. Which suffers from challenges in interpreting the internal workings of the model, particularly when neurons encode multiple unrelated features. In this paper, we propose a novel framework that transitions the focus from analyzing individual neurons to investigating groups of neurons, shifting the emphasis from neuron-output relationships to functional interaction between neurons. Our automated framework, NeurFlow, first identifies core neurons and clusters them into groups based on shared functional relationships, enabling a more coherent and interpretable view of the network's internal processes. This approach facilitates the construction of a hierarchical circuit representing neuron interactions across layers, thus improving interpretability while reducing computational costs. Our extensive empirical studies validate the fidelity of our proposed NeurFlow. Additionally, we showcase its utility in practical applications such as image debugging and automatic concept labeling, thereby highlighting its potential to advance the field of neural network explainability.