Model Evaluation and Anomaly Detection in Temporal Complex Networks using Deep Learning Methods

2024-06-15

arXiv.org

AI Summary

Existing dynamic network generation models lack effective evaluation metrics and structural anomaly detection mechanisms. Method: This paper proposes the first end-to-end deep learning framework that jointly addresses generative quality assessment and unsupervised anomaly identification. It innovatively integrates graph neural networks with temporal encoders to jointly model topological snapshot sequences, learning interpretable anomaly scores directly from reconstruction errors—thereby transcending static evaluation paradigms and inherently accommodating dynamic network evolution. Results: Experiments on five real-world temporal network datasets demonstrate that the framework reduces average evaluation error by 23.6% compared to conventional baselines, achieving substantial improvements in both assessment accuracy and robustness of anomaly detection.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Planning, Routing, and Scheduling: Temporal Planning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Modeling complex networks allows us to analyze the characteristics and discover the basic mechanisms governing phenomena such as disease outbreaks, information diffusion, transportation efficiency, social influence, and even human brain function. Consequently, various network generative models (called temporal network models) have been presented to model how the network topologies evolve dynamically over time. Temporal network models face the challenge of results evaluation because common evaluation methods are appropriate only for static networks. This paper proposes an automatic approach based on deep learning to handle this issue. In addition to an evaluation method, the proposed method can also be used for anomaly detection in evolving networks. The proposed method has been evaluated on five different datasets, and the evaluations show that it outperforms the alternative methods based on the error rate measure in different datasets.

Problem

• Evaluating generative models for dynamic network evolution accuracy
• Detecting anomalies in temporal network structural changes
• Overcoming limitations of static network evaluation methods

Innovation

• Integrates graph convolutional networks with dynamic signal processing
• Uses attention mechanism to capture dynamic structural changes
• Evaluates network snapshots against expected temporal evolution