Skip to yearly menu bar Skip to main content


Graph Neural Networks Inspired by Classical Iterative Algorithms

Yang Yongyi · Tang Liu · Yangkun Wang · Jinjing Zhou · Quan Gan · Zhewei Wei · Zheng Zhang · Zengfeng Huang · David Wipf

[ ] [ Livestream: Visit Representation Learning 6 ] [ Paper ]
[ Paper ]


Despite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to oversmoothing, long-range dependencies, and spurious edges, e.g., as can occur as a result of graph heterophily or adversarial attacks. To at least partially address these issues within a simple transparent framework, we consider a new family of GNN layers designed to mimic and integrate the update rules of two classical iterative algorithms, namely, proximal gradient descent and iterative reweighted least squares (IRLS). The former defines an extensible base GNN architecture that is immune to oversmoothing while nonetheless capturing long-range dependencies by allowing arbitrary propagation steps. In contrast, the latter produces a novel attention mechanism that is explicitly anchored to an underlying end-to-end energy function, contributing stability with respect to edge uncertainty. When combined we obtain an extremely simple yet robust model that we evaluate across disparate scenarios including standardized benchmarks, adversarially-perturbated graphs, graphs with heterophily, and graphs involving long-range dependencies. In doing so, we compare against SOTA GNN approaches that have been explicitly designed for the respective task, achieving competitive or superior node classification accuracy. Our code is available at And for an extended version of this work, please see

Chat is not available.