Enhancing GNNs Performance on Combinatorial Optimization by Recurrent Feature Update

TL;DR

This paper introduces QRF-GNN, a novel recurrent feature update method for GNNs that significantly improves solution quality and scalability for combinatorial optimization problems formulated as QUBO, outperforming existing learning-based methods.

Contribution

The paper proposes a new recurrent GNN architecture with dynamic feature updates that enhances solution quality for QUBO-based combinatorial optimization problems.

Findings

QRF-GNN outperforms existing learning-based approaches.

QRF-GNN achieves results comparable to state-of-the-art heuristics.

The method scales effectively to large problem instances.

Abstract

Combinatorial optimization (CO) problems are crucial in various scientific and industrial applications. Recently, researchers have proposed using unsupervised Graph Neural Networks (GNNs) to address NP-hard combinatorial optimization problems, which can be reformulated as Quadratic Unconstrained Binary Optimization (QUBO) problems. GNNs have demonstrated high performance with nearly linear scalability and significantly outperformed classic heuristic-based algorithms in terms of computational efficiency on large-scale problems. However, when utilizing standard node features, GNNs tend to get trapped to suboptimal local minima of the energy landscape, resulting in low quality solutions. We introduce a novel algorithm, denoted hereafter as QRF-GNN, leveraging the power of GNNs to efficiently solve CO problems with QUBO formulation. It relies on unsupervised learning by minimizing the loss function derived from QUBO relaxation. The proposed key components of the architecture include the recurrent use of intermediate GNN predictions, parallel convolutional layers and combination of static node features as input. Altogether, it helps to adapt the intermediate solution candidate to minimize QUBO-based loss function, taking into account not only static graph features, but also intermediate predictions treated as dynamic, i.e. iteratively changing recurrent features. The performance of the proposed algorithm has been evaluated on the canonical benchmark datasets for maximum cut, graph coloring and maximum independent set problems. Results of experiments show that QRF-GNN drastically surpasses existing learning-based approaches and is comparable to the state-of-the-art conventional heuristics, improving their scalability on large instances.