Exact Graph Learning via Integer Programming

2026-01-28

AI Summary

This work addresses the challenge of accurately inferring the dependency structure among variables—represented as a graph—without relying on strong assumptions while guaranteeing global optimality. The authors formulate graph learning as an integer programming problem, uniquely integrating nonparametric conditional independence tests with an efficient encoding of graph separation criteria. This approach rigorously ensures global optimality and supports the exact recovery of diverse graph classes, including directed acyclic graphs, mixed graphs, and chain graphs. Evaluated on both synthetic and benchmark datasets, the method achieves state-of-the-art performance, outperforms existing exact algorithms in computational speed, and scales effectively to larger graph structures.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Learning the dependence structure among variables in complex systems is a central problem across medical, natural, and social sciences. These structures can be naturally represented by graphs, and the task of inferring such graphs from data is known as graph learning or as causal discovery if the graphs are given a causal interpretation. Existing approaches typically rely on restrictive assumptions about the data-generating process, employ greedy oracle algorithms, or solve approximate formulations of the graph learning problem. As a result, they are either sensitive to violations of central assumptions or fail to guarantee globally optimal solutions. We address these limitations by introducing a nonparametric graph learning framework based on nonparametric conditional independence testing and integer programming. We reformulate the graph learning problem as an integer-programming problem and prove that solving the integer-programming problem provides a globally optimal solution to the original graph learning problem. Our method leverages efficient encodings of graphical separation criteria, enabling the exact recovery of larger graphs than was previously feasible. We provide an implementation in the openly available R package'glip'which supports learning (acyclic) directed (mixed) graphs and chain graphs. From the resulting output one can compute representations of the corresponding Markov equivalence classes or weak equivalence classes. Empirically, we demonstrate that our approach is faster than other existing exact graph learning procedures for a large fraction of instances and graphs of various sizes. GLIP also achieves state-of-the-art performance on simulated data and benchmark datasets across all aforementioned classes of graphs.

Problem

• graph learning
• causal discovery
• conditional independence
• integer programming
• Markov equivalence

Innovation

• Integer Programming
• Exact Graph Learning
• Nonparametric Conditional Independence
• Graphical Models
• Causal Discovery