Embedding-aware Polarization Management in Signed Networks

TL;DR

This paper introduces EPM, a framework for measuring and reducing polarization in signed network embeddings, improving analysis without distorting network structure.

Contribution

EPM provides a novel embedding-based polarization measure and a structure-aware mitigation strategy for signed networks.

Findings

EPM effectively reduces polarization in real-world signed networks.

EPM preserves task-relevant network structures.

The framework is validated through experiments on multiple datasets.

Abstract

Signed network embeddings (SNE) are widely used to represent networks with positive and negative relations, but their repeated use in downstream analysis pipelines can inadvertently reinforce structural polarization. Existing polarization measures are largely designed for unsigned networks or rely on predefined opinion states, limiting their applicability to embedding-based analysis in signed settings. We propose EPM, a unified polarization management framework that jointly measures and mitigates polarization in the embedding space. EPM introduces an embedding-based polarization measure grounded in effective resistance and a structure-aware mitigation strategy via localized augmentation through structurally balanced intermediary nodes. Experiments on real-world signed networks demonstrate that EPM effectively mitigates polarization while preserving task-relevant network structure. The codebase of EPM is available at https://github.com/JeonghanSon/EPM-Embedding-aware-Polarization-Management.