2016-Structural Deep Network Embedding
文章目录 ABSTRACT 1. INTRODUCTION 2. RELATED WORK 2.1 Deep Neural Network 2.2 Network Embedding 3. STRUCTURAL DEEP NETWORK EMBEDDING 3.1 Problem Definition 3.2 The Model 3.2.1 Framework 3.2.2 Loss Functions 3.2.3 Optimization 3.3 Analysis and Discussions 4. EXPERIMENTS 4.1 Datasets 4.2 Baseline Algorithms 4.3 Evaluation Metrics 4.4 Parameter Settings 4.5 Experiment Results 4.5.1 Network Reconstruction 4.5.2 Multi-label Classification 4.5.3 Link Prediction 4.5.4 Visualization 4.6 Parameter Sensitivity 5. CONCLUSIONS ABSTRACT 网络嵌入是学习网络中顶点的低维表示的一种重要方法,旨在捕获和保留网络结构。几乎所有现有的网络嵌入方法都采用浅层模型。但是