AI RESEARCH
Learning to Approximate Uniform Facility Location via Graph Neural Networks
arXiv CS.LG
•
ArXi:2602.13155v2 Announce Type: replace Neural networks, particularly message-passing neural networks (MPNNs), are increasingly used as heuristics for hard combinatorial optimization problems. Yet many learning-based methods rely on supervision, reinforcement learning, or gradient estimators, causing high computational cost, unstable