A generalized motif-based Naïve Bayes model for sign prediction in complex networks

2025-12-27

AI Summary

Link sign prediction in signed complex networks suffers from the oversimplified assumption in traditional Naïve Bayes models that all neighboring nodes contribute equally, ignoring their heterogeneous structural roles. Method: We propose a novel “role function” to quantify heterogeneous neighbor contributions, breaking the uniform-neighborhood assumption. Based on this, we develop the Generalized Multi-motif Naïve Bayes (GMNB) model and its feature-driven variant (FGMNB), which jointly support adaptive motif selection and high-dimensional feature embedding. Furthermore, we integrate multi-motif linear combination with XGBoost/LightGBM ensemble learning. Contribution/Results: Evaluated on four real-world signed networks, our models significantly outperform five state-of-the-art embedding methods. Crucially, we identify motif-type heterogeneity across datasets—i.e., different dominant predictive motifs emerge in different networks—thereby empirically validating the necessity of modeling local structural sensitivity and motif-aware neighborhood heterogeneity.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Signed networks, encoding both positive and negative interactions, are essential for modeling complex systems in social and financial domains. Sign prediction, which infers the sign of a target link, has wide-ranging practical applications. Traditional motif-based Naïve Bayes models assume that all neighboring nodes contribute equally to a target link's sign, overlooking the heterogeneous influence among neighbors and potentially limiting performance. To address this, we propose a generalizable sign prediction framework that explicitly models the heterogeneity. Specifically, we design two role functions to quantify the differentiated influence of neighboring nodes. We further extend this approach from a single motif to multiple motifs via two strategies. The generalized multiple motifs-based Naïve Bayes model linearly combines information from diverse motifs, while the Feature-driven Generalized Motif-based Naïve Bayes (FGMNB) model integrates high-dimensional motif features using machine learning. Extensive experiments on four real-world signed networks show that FGMNB consistently outperforms five state-of-the-art embedding-based baselines on three of these networks. Moreover, we observe that the most predictive motif structures differ across datasets, highlighting the importance of local structural patterns and offering valuable insights for motif-based feature engineering. Our framework provides an effective and theoretically grounded solution to sign prediction, with practical implications for enhancing trust and security in online platforms.

Problem

• Predicts link signs in signed networks using motif heterogeneity.
• Models neighbor influence via role functions and multiple motifs.
• Improves accuracy over baselines with dataset-specific motif patterns.

Innovation

• Generalized motif-based Naive Bayes model for sign prediction
• Role functions quantify heterogeneous influence of neighboring nodes
• Feature-driven model integrates high-dimensional motif features via machine learning