Assessing the Robustness and Reducibility of Multiplex Networks with Embedding-Aided Interlayer Similarities

2025-05-11

AI Summary

Existing methods for inter-layer similarity modeling in multiplex networks encode only local information, failing to capture their dual geometric and structural complexity. To address this, we propose EATSim—a novel embedding-augmented inter-layer similarity modeling framework—that jointly captures intra-layer topological similarity and cross-layer anchor alignment consistency, thereby overcoming the limitations of single-view embeddings. By co-optimizing graph embedding learning and anchor alignment, EATSim explicitly encodes geometric similarity across layers. Extensive experiments on synthetic and real-world multiplex networks demonstrate that EATSim significantly improves inter-layer similarity estimation accuracy. Moreover, it achieves state-of-the-art performance on two downstream tasks: robustness prediction and network reducibility assessment. Our work establishes a new paradigm for analyzing complex interconnected systems through principled, geometry-aware, multi-layer representation learning.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Analogy
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Social Networks and Social Media: Social media analysis through the lenses of networks

Abstract

The study of interlayer similarity of multiplex networks helps to understand the intrinsic structure of complex systems, revealing how changes in one layer can propagate and affect others, thus enabling broad implications for transportation, social, and biological systems. Existing algorithms that measure similarity between network layers typically encode only partial information, which limits their effectiveness in capturing the full complexity inherent in multiplex networks. To address this limitation, we propose a novel interlayer similarity measuring approach named Embedding Aided inTerlayer Similarity (EATSim). EATSim concurrently incorporates intralayer structural similarity and cross-layer anchor node alignment consistency, providing a more comprehensive framework for analyzing interconnected systems. Extensive experiments on both synthetic and real-world networks demonstrate that EATSim effectively captures the underlying geometric similarities between interconnected networks, significantly improving the accuracy of interlayer similarity measurement. Moreover, EATSim achieves state-of-the-art performance in two downstream applications: predicting network robustness and network reducibility, showing its great potential in enhancing the understanding and management of complex systems.

Problem

• Measure interlayer similarity in multiplex networks comprehensively
• Improve accuracy of network layer similarity algorithms
• Enhance prediction of network robustness and reducibility

Innovation

• Embedding-Aided Interlayer Similarity (EATSim) approach
• Combines intralayer structure and anchor alignment
• Improves accuracy in network similarity measurement