Self-Paced Learning Based Graph Convolutional Neural Network for Mixed Integer Programming (Student Abstract)

Graph convolutional neural network (GCN) based methods have achieved noticeable performance in solving mixed integer programming problems (MIPs). However, the generalization of existing work is limited due to problem structure. This paper proposes a self-paced learning (SPL) GCN (SPGCN) with curriculum (CL) make utmost samples. SPGCN employs model imitate branching variable selection during branch and bound process, while training process conducted fashion. Specifically, contains loss-based automatic difficulty measurer, where loss sample represents level. In each iteration, dynamic dataset constructed according level for training. Experiments on four NP-hard datasets verify that CL can lead improvement convergence speedup MIPs, SPL performs better than predefined methods.