CSBA-Net: Learning Cross-Scale Structural Dependencies for Influential Node Identification in Complex Networks

Identifying influential nodes is a fundamental task in complex network analysis, with applications in epidemic control, information diffusion, and network robustness. Existing centrality-based and learning-based methods often provide limited integration of structural information across different network scales. To address this limitation, we propose CSBA-Net, for Cross-Scale Structural BiGRU Attention Network, a multi-scale structural represen-tation learning framework that jointly captures local, community-level, and global structural patterns. The extracted representations are processed by CNNs and integrated through a BiGRU with multi-head self-attention to model dependencies across structural scales. Influential-node scores are learned through regression using SIR-based diffusion simulations as reference targets. We conduct experiments on 24 real-world and 12 synthetic networks from social, biological, technological, and knowledge domains, and show that CSBA-Net achieves Kendall’s τ = 0.802, Spearman’s ρ = 0.943, NDCG@10 = 0.898, and NDCG@20 = 0.916, outperforming the considered centrality-, CNN-, and GNN-based baselines. The results demonstrate the effectiveness of combining complementary structural scales for ac-curate influential-node ranking across diverse network structures.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-19
DOI
https://doi.org/10.21203/rs.3.rs-11432969/v1
Primary Topic
Complex Network Analysis Techniques
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

CSBA-Net: Learning Cross-Scale Structural Dependencies for Influential Node Identification in Complex Networks

Mohammed Lalou, Nardjes Bouchemal, Rihab Boukheche
4 links
Research Square
Complex Network Analysis Techniques
preprint

CSBA-Net: Learning Cross-Scale Structural Dependencies for Influential Node Identification in Complex Networks

Mohammed Lalou, Nardjes Bouchemal, Rihab Boukheche
preprint en

Abstract

Identifying influential nodes is a fundamental task in complex network analysis, with applications in epidemic control, information diffusion, and network robustness. Existing centrality-based and learning-based methods often provide limited integration of structural information across different network scales. To address this limitation, we propose CSBA-Net, for Cross-Scale Structural BiGRU Attention Network, a multi-scale structural represen-tation learning framework that jointly captures local, community-level, and global structural patterns. The extracted representations are processed by CNNs and integrated through a BiGRU with multi-head self-attention to model dependencies across structural scales. Influential-node scores are learned through regression using SIR-based diffusion simulations as reference targets. We conduct experiments on 24 real-world and 12 synthetic networks from social, biological, technological, and knowledge domains, and show that CSBA-Net achieves Kendall’s τ = 0.802, Spearman’s ρ = 0.943, NDCG@10 = 0.898, and NDCG@20 = 0.916, outperforming the considered centrality-, CNN-, and GNN-based baselines. The results demonstrate the effectiveness of combining complementary structural scales for ac-curate influential-node ranking across diverse network structures.

Research Square
Université de Bourgogne (FR), Laboratoire d'Informatique et d'Automatique pour les Systèmes (FR), Littérature, Idéologies, Représentations aux XVIIIe et XIXe Siècles (FR), Laboratoire d'Informatique de Bourgogne (FR)
Complex Network Analysis Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon