Verifying message-passing neural networks via topology-based bounds tightening

arXiv:2402.13937v1 Announce Type: cross
Abstract: Since graph neural networks (GNNs) are often vulnerable to attack, we need to know when we can trust them. We develop a computationally effective approach towards providing robust certificates for message-passing neural networks (MPNNs) using a Rectified Linear Unit (ReLU) activation function. Because our work builds on mixed-integer optimization, it encodes a wide variety of subproblems, for example it admits (i) both adding and removing edges, (ii) both global and local budgets, and (iii) both …

abstract arxiv cs.lg function gnns graph graph neural networks linear math.oc networks neural networks relu robust them topology trust type via vulnerable work