Comparison of hyperbolic embedding methods for real-world networks: Machine Learning versus Network Science

Sun, 01 Jun 2025 00:00:00 +0000

Overview

This thesis, authored by Zhou Haojie at the Cyprus University of Technology, presents a comprehensive comparative study of hyperbolic embedding methods applied to real-world networks, focusing on the intersection and contrast between machine learning approaches and traditional network science techniques. Hyperbolic embeddings have become a powerful tool for representing complex network data, enabling more efficient analysis of structural properties and facilitating downstream tasks such as link prediction, classification, and anomaly detection. The work is situated at the confluence of two rapidly evolving fields—machine learning and network science—each offering distinct methodologies for network representation and analysis.

Key Contributions

Systematic Comparison: The thesis systematically compares state-of-the-art hyperbolic embedding methods from both machine learning and network science perspectives. It evaluates their performance on a variety of real-world networks, considering multiple downstream tasks such as mapping accuracy, greedy routing, and link prediction. This dual perspective allows for a nuanced understanding of the strengths and limitations inherent to each methodological tradition.
Evaluation Metrics: The study employs a range of quantitative metrics to assess embedding quality, including computational complexity, scalability, and sensitivity to network characteristics like degree distribution, modularity, and clustering coefficient. By doing so, it provides a holistic view of how different embedding strategies perform under diverse network conditions.
Integration of Approaches: The thesis explores the potential for integrating data-driven machine learning models with model-based network science methods. It highlights the flexibility of machine learning approaches, which do not rely on strong generative assumptions, and contrasts this with the interpretability and theoretical grounding of network science models. The work also discusses recent advances in embedding multilayer networks and the use of the Poincaré disk model for improved geometric representation and interpretability.
Practical Insights: Through extensive experimentation, the thesis identifies practical trade-offs between embedding accuracy, computational efficiency, and applicability to different types of networks. It offers guidance for practitioners on selecting appropriate embedding methods based on specific network properties and analytic goals.

Impact and Relevance

This thesis makes a significant contribution to both the theoretical and practical understanding of hyperbolic network embeddings. By bridging the gap between machine learning and network science, it advances the state of the art in network representation learning and provides actionable insights for researchers and practitioners working with complex network data. The findings are particularly relevant for applications in social network analysis, biological network modeling, cybersecurity, and any domain where understanding the latent geometry of networked systems is crucial. The comparative framework and recommendations established in this work are poised to inform future research and development of more robust, scalable, and interpretable network embedding algorithms.

Predictability of complex networks

Sun, 01 Jun 2025 00:00:00 +0000

Overview

This master’s thesis, titled Predictability of complex networks by Xuetong Zhao, investigates the fundamental question of how predictable the behavior and evolution of complex networks are. Complex networks—such as social, biological, and technological systems—exhibit intricate structures and dynamic behaviors that challenge traditional analytical methods. The thesis is situated within the Department of Electrical Engineering, Computer Engineering, and Informatics at Cyprus University of Technology, and was completed under the supervision of Fragkiskos Papadopoulos in February 2024.

The work addresses the theoretical and practical aspects of network predictability, exploring the extent to which future states or structural changes in a network can be anticipated based on current information. The study leverages recent advances in network science, statistical mechanics, and computational modeling to analyze both synthetic and real-world network data.

Key Contributions

Theoretical Framework: The thesis develops a rigorous framework for quantifying predictability in complex networks. This includes defining appropriate metrics and criteria for assessing how well future network configurations or dynamics can be forecasted from present data.
Methodological Advances: It introduces or adapts analytical and computational techniques—potentially including machine learning, statistical inference, and random walk models—to assess and improve predictability. The work may also compare the effectiveness of different approaches across various types of networks.
Empirical Evaluation: The research applies the proposed methods to a range of network datasets, demonstrating how predictability varies with network topology, size, and the nature of interactions. Results likely highlight which structural features (e.g., degree distribution, clustering, modularity) enhance or limit predictability.
Case Studies: By examining specific real-world networks (such as social, communication, or biological systems), the thesis illustrates the practical implications of its findings, showing how predictability insights can inform network design, intervention strategies, or risk assessment.

Impact and Relevance

The thesis makes significant contributions to the field of network science by clarifying the limits and possibilities of predicting complex network behavior. Understanding predictability is crucial for a wide range of applications, including epidemic modeling, infrastructure resilience, information diffusion, and cybersecurity. By providing a systematic approach to measuring and enhancing predictability, the research offers valuable tools for scientists and engineers working with complex systems.

Moreover, the findings have broader implications for the design and management of networked systems. Improved predictability can lead to more effective control strategies, better resource allocation, and enhanced robustness against failures or attacks. The thesis thus serves as a bridge between theoretical insights and practical applications, advancing both the science and engineering of complex networks.

network science | MSc in Electronics and Technology

Comparison of hyperbolic embedding methods for real-world networks: Machine Learning versus Network Science

Overview

Key Contributions

Impact and Relevance

Predictability of complex networks

Overview

Key Contributions

Impact and Relevance