Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Son, Jeonghan, Han, Kyungsik, Lee, Yeon-Chang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2602.21755
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914350332116992
author Son, Jeonghan
Han, Kyungsik
Lee, Yeon-Chang
author_facet Son, Jeonghan
Han, Kyungsik
Lee, Yeon-Chang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_21755
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Embedding-aware Polarization Management in Signed Networks
Son, Jeonghan
Han, Kyungsik
Lee, Yeon-Chang
Social and Information Networks
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.
title Embedding-aware Polarization Management in Signed Networks
topic Social and Information Networks
url https://arxiv.org/abs/2602.21755