Salvato in:
Dettagli Bibliografici
Autori principali: Hadou, Samar, Ribeiro, Alejandro
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.17156
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910006426730496
author Hadou, Samar
Ribeiro, Alejandro
author_facet Hadou, Samar
Ribeiro, Alejandro
contents In this paper, we unroll the dynamics of the dual ascent (DA) algorithm in two coupled graph neural networks (GNNs) to solve constrained optimization problems. The two networks interact with each other at the layer level to find a saddle point of the Lagrangian. The primal GNN finds a stationary point for a given dual multiplier, while the dual network iteratively refines its estimates to reach an optimal solution. We force the primal and dual networks to mirror the dynamics of the DA algorithm by imposing descent and ascent constraints. We propose a joint training scheme that alternates between updating the primal and dual networks. Our numerical experiments demonstrate that our approach yields near-optimal near-feasible solutions and generalizes well to out-of-distribution (OOD) problems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17156
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unrolled Graph Neural Networks for Constrained Optimization
Hadou, Samar
Ribeiro, Alejandro
Machine Learning
In this paper, we unroll the dynamics of the dual ascent (DA) algorithm in two coupled graph neural networks (GNNs) to solve constrained optimization problems. The two networks interact with each other at the layer level to find a saddle point of the Lagrangian. The primal GNN finds a stationary point for a given dual multiplier, while the dual network iteratively refines its estimates to reach an optimal solution. We force the primal and dual networks to mirror the dynamics of the DA algorithm by imposing descent and ascent constraints. We propose a joint training scheme that alternates between updating the primal and dual networks. Our numerical experiments demonstrate that our approach yields near-optimal near-feasible solutions and generalizes well to out-of-distribution (OOD) problems.
title Unrolled Graph Neural Networks for Constrained Optimization
topic Machine Learning
url https://arxiv.org/abs/2509.17156