GraphBU

GraphBU: Graph-native block unit generator for MILP instances improves solver training data

GraphBU is a new method for generating synthetic Mixed-Integer Linear Programming (MILP) instances using graph-native block units that explicitly encode how local subproblems couple to the rest of an instance. The approach achieves ~0.934 average graph-statistical similarity to source families, ~96.7% feasibility preservation, and ~8% improvement in downstream Predict-and-Search training performance. The work addresses a practical bottleneck in ML-for-combinatorial-optimization research: the scarcity of realistic MILP instances from private or proprietary pipelines.