PulseAugur
EN
LIVE 10:10:34

GraphBU generator creates MILP instances with graph-native units

Researchers have developed GraphBU, a novel graph-native generator for creating Mixed Integer Linear Programming (MILP) instances. This method utilizes local subproblems with their interfaces as basic units, promoting the coupling of nodes into master constraints or boundary variables. GraphBU aims to preserve the structural properties of MILP instances, which is crucial for solver development and training learned policies. The generator has demonstrated success in maintaining graph statistics similar to source families, preserving feasibility on datasets, and improving downstream Predict-and-Search training. AI

IMPACT Improves the generation of structured data for training machine learning models in optimization.

RANK_REASON The cluster contains a research paper detailing a new method for generating MILP instances.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

GraphBU generator creates MILP instances with graph-native units

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Xiaolei Guo, Chenyu Zhou, Jianghao Lin, Dongdong Ge ·

    GraphBU: MILP Instance Generation with Graph-Native Block Units

    arXiv:2607.06532v1 Announce Type: new Abstract: Mixed-integer linear programming (MILP) instances used for solver development are hard to obtain when models come from private or application-specific pipelines. A generator must keep the structure that solvers and learned policies …

  2. arXiv cs.LG TIER_1 English(EN) · Dongdong Ge ·

    GraphBU: MILP Instance Generation with Graph-Native Block Units

    Mixed-integer linear programming (MILP) instances used for solver development are hard to obtain when models come from private or application-specific pipelines. A generator must keep the structure that solvers and learned policies rely on. Existing general generators usually cho…