Leveraging Trustworthy Node Attributes for Effective Network Alignment

다국어 초록 (Multilingual Abstract)

With the prevalence of social media platforms, accurately identifying the same users across different networks through network alignment has become crucial. Existing methods often struggle due to sparse or absent user-identifiable information (node attributes), highlighting the need for augmenting node attributes. However, research on attribute augmentation remains largely under-explored.
In this study, we aim to design augmented attributes that enhance network alignment by reflecting three key structural Characteristics: (C1) global structural characteristic, reflects the global network structure; (C2) seed-based structural characteristic, leverages cross-network structural information associated with seed nodes; (C3) multi-aspect structural characteristic, employs diverse structural relationship measures.
To this end, we propose a novel approach for designing trustworthy Augmented Seed-baSed and multI-aspect STructurAl iNformaTion (ASSISTANT) attributes. To enhance alignment performance, we also present a learning module that utilizes a gate mechanism to select the most effective measure dynamically.
Extensive experiments across various datasets demonstrate the following: 1) Our network alignment framework, which includes a gate mechanism module, significantly out- performs state-of-the-art methods in alignment accuracy; 2) other state-of-the-art methods using ASSISTANT attributes as input substantially boosts their own alignment accuracy; and 3) us ing only ASSISTANT attributes without any training process also leads to effective alignment, showcasing their high trustworthiness.

목차 (Table of Contents)

• 1 Chapter I Introduction 1
• 2 Chapter II Relational Work 6
• 3 Chapter III Preliminaries 8
• 4 Chapter IV Proposed Method 12
• 4.1 Overview 12
• 4.2 Objective Formulation 13
• 4.3 ASSISTANT attributes 13
• 4.4 Alignment Framework 15
• 4.4.1 Information Selection Gate 15
• 4.4.2 Weight sharing GCN 16
• 4.4.3 Reconstruction Loss 17
• 4.4.4 Node Alignment 17
• 5 Chapter V EXPERIMENTS 18
• 5.1 Experimental Setup 18
• 5.1.1 Datasets 18
• 5.1.2 Baselines 19
• 5.1.3 Performance metrics 21
• 5.1.4 Implementation Details 21
• 5.2 Results 23
• 5.2.1 RQ1: Comparison with the competitors 23
• 5.2.2 RQ2: Orthogonality of ASSISTANT attributes 25
• 5.2.3 RQ3: Comparison between Relationship Measures 26
• 5.2.4 RQ4: Ablation Study on the Gate Mechanism 28
• 5.2.5 RQ5: Efficiency Study 29
• 6 Chapter VII Conclusions 30
• References 31
• Abstract (in Korean) 39
• Acknowledgment 40