Analyzing Neural Network Robustness Using Graph Curvature
It addresses neural network robustness for AI safety and reliability, but appears incremental as it applies an existing graph theory concept to a new domain.
This paper tackles the problem of neural network robustness by analyzing it through graph curvature, specifically defining neural Ricci curvature to identify bottleneck edges, and finds on MNIST that these edges correlate with reduced robustness, suggesting a basis for new robust training methods.
This paper presents a new look at the neural network (NN) robustness problem, from the point of view of graph theory analysis, specifically graph curvature. Graph curvature (e.g., Ricci curvature) has been used to analyze system dynamics and identify bottlenecks in many domains, including road traffic analysis and internet routing. We define the notion of neural Ricci curvature and use it to identify bottleneck NN edges that are heavily used to ``transport data" to the NN outputs. We provide an evaluation on MNIST that illustrates that such edges indeed occur more frequently for inputs where NNs are less robust. These results will serve as the basis for an alternative method of robust training, by minimizing the number of bottleneck edges.