Skip to content
Preprint

Graph Neural Networks for Scalable and Transferable Node Centrality Approximation

Jul 2026 · 0 citations · 28 references
Computer Science

TL;DR

Results show that mixed-distribution training can improve structural transfer in GNN-based centrality approximation, while identifying closeness centrality's sensitivity to topology as an open challenge.

Abstract

Graph Neural Networks (GNNs) provide a learning-based framework for approximating graph quantities that are expensive to compute exactly. This paper investigates GNNs for scalable approximation of betweenness and closeness centrality, formulated as a node-ranking problem. Exact centrality values are used as supervision, and ranking quality is evaluated using Kendall's tau rank correlation. We study whether message-passing GNNs can learn transferable structural representations across different graph topologies rather than only fitting the distribution used during training. On unseen Erdos renyi graphs, the proposed models achieve tau = 0.851 for betweenness and tau = 0.894 for closeness. A large-scale betweenness model trained on graphs with N = 5,000 nodes achieves tau = 0.938, demonstrating scalability. Mixed-distribution training on Erdos renyi, Barabasi-Albert, and Gaussian Random Partition graphs improves betweenness transfer across graph families. In contrast, closeness centrality remains more sensitive to community-structured graphs and shows reduced transfer to real-world topologies. Finally, GNN inference achieves up to a 97.7x speedup over exact computation. These results show that mixed-distribution training can improve structural transfer in GNN-based centrality approximation, while identifying closeness centrality's sensitivity to topology as an open challenge.

View source

Similar papers

Open access Aug 2026

Beyond PageRank in GraphHD: Centrality Metrics and Efficient Hyperdimensional Encodings

Experiments show that replacing PageRank with alternative centralities yields similar F1-scores while offering notable runtime savings, and that GraphHD-Order remains competitive with the original GraphHD baseline while providing consistent speedups in encoding time.

Ignacio Sica, Gustavo Vazquez · 0 citations
Jul 2026

Enhancing link prediction in complex networks using GraphSAGE with graph diffusion convolution

A diffusion-enhanced inductive link prediction framework that combines Graph Diffusion Convolution (GDC), structural node descriptors, and neighborhood aggregation from GraphSAGE is proposed that achieves higher accuracy than the other models on the benchmark datasets.

Indu, Jyoti Arora, Pooja Kherwa et al. · 0 citations
Preprint Jul 2026

Graph Classification via Network Usable Information: From Representation Evaluation to Structure Selection

A training-free NUI estimation procedure based on clustering consistency with ground-truth labels is introduced, providing a proxy for task-relevant information without supervised learning, and a strong correlation between estimated NUI and downstream classification accuracy is observed, validating NUI as an effective measure of representation utility.

A. Shaik, Anwar Said · 0 citations
Conference Jul 2026

Statistical Edge Graphs for Tabular Learning with Graph Neural Networks

Tabular data are central to many real-world applications, yet deep learning models often underperform compared to tree-based methods due to limited relational inductive bias. We propose a unified framework that models each tabular instance as an instance-level statistical feature graph to enable learning with Graph Neural Networks (GNNs). In this representation, features are treated as nodes, and edges encode pairwise statistical relationships derived from Z-score similarity, covariance, Pearson correlation, or Euclidean distance. This formulation explicitly captures inter-feature dependencies rather than relying solely on implicitly learned interactions. We evaluate the framework across four classification and four regression datasets spanning diverse domains and feature dimensionalities. Results demonstrate competitive and, in several cases, superior performance compared to strong baselines including Random Forests, XGBoost, and multilayer perceptrons. Correlation- and covariance-based edge constructions consistently provide robust performance across tasks. Furthermore, empirical analysis indicates that performance gains become more pronounced in higher-dimensional datasets, suggesting that graph-based representations are particularly effective at modeling complex feature interactions. Overall, this work provides a systematic examination of statistical graph construction for tabular learning and highlights the potential of GNNs as a structured alternative to conventional tabular models.

Shashank Parmar · 0 citations
Jul 2026

LIGR: Label Informativeness-guided Graph Rewiring

This work proposes LIGR (Label Informativeness-Guided Rewiring), which maximizes an information-theoretic measure quantifying how much neighbors’ labels reveal about node labels, suitable for applications requiring interpretability (biological networks, social graphs).

Rucha Bhalchandra Joshi, Subhankar Mishra · 0 citations
Review Jun 2026

Graph Neural Networks Applications Across Domains: All Insights You Need

This survey organises the field around a single design space, derives the spectral and spatial formulations from shared first principles, and connects expressive power to the Weisfeiler-Leman hierarchy with explicit statements of what current architectures can and cannot separate.

Abderaouf Bahi · 1 citation