Unrolled Graph Neural Networks for Constrained Optimization
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Constrained Optimization Perspective of Unrolled Transformers
We introduce a constrained optimization framework for training transformers that behave like optimization descent algorithms. Specifically, we enforce layerwise descent constraints on the objective function and replace s…
Text ClassificationVideo DenoisingHUANet: Hard-Constrained Unrolled ADMM for Constrained Convex Optimization
This paper presents HUANet, a constrained deep neural network architecture that unrolls the iterations of the Alternating Direction Method of Multipliers (ADMM) into a trainable neural network for solving constrained con…
Learning Structured Sparse Matrices for Signal Recovery via Unrolled Optimization
Countless signal processing applications include the reconstruction of an unknown signal from very few indirect linear measurements. Because the measurement operator is commonly constrained by the hardware or the physics…
compressed sensingRolling Shutter CorrectionAnalyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization
The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks. A central challenge in this setting is backpropagation through the solut…
Unrolling Plug-and-Play Gradient Graph Laplacian Regularizer for Image Restoration
Generic deep learning (DL) networks for image restoration like denoising and interpolation lack mathematical interpretability, require voluminous training data to tune a large parameter set, and are fragile in the face o…
DenoisingGraph LearningImage Restoration