Graph4BiLO: Graph Neural Network Approximation for Bilevel Mixed-Integer Linear Optimization
Graph4BiLO is introduced, a graph neural network (GNN) approach for learning bilevel value functions from variable--constraint graph representations that obtains objective values comparable to Neur2BiLO across all tested sizes while avoiding size-specific neural networks.
Jessica D. Elrefaei, Kaixun Hua, Seungbae Kim et al.
· 0 citations