Intro
Preface
Organization
Contents
Knowledge Graph
Temporal Knowledge Graph Embedding for Link Prediction
1 Introduction
2 Related Work
3 Problem Formulation
4 Methodology
4.1 Structural Self-attention
4.2 Temporal Self-attention
4.3 Parameter Learning
4.4 Discussion
5 Experiments
5.1 Experimental Settings
5.2 Performance Comparison (RQ1)
5.3 Utility of Structural and Temporal Self-attention (RQ2)
5.4 Hyper-Parameter Studies (RQ3)
6 Conclusions
References
A Multi-modal Knowledge Graph Platform Based on Medical Data Lake

1 Introduction
2 Related Work
3 Architecture of MMKGP
4 Translation-Based Model Enhanced by Prior Knowledge
4.1 TransE Model
4.2 Constraint for Relations
5 Knowledge Graph Completion with Multi-modal Data
5.1 Dataset
5.2 Evaluation Criterion
5.3 Model Training and Result
6 Knowledge Graph-Based Clinical Decision Support System
6.1 Link Prediction & Correction
6.2 Recommendation and Q&A System
7 Conclusion
References
Fusion of Natural Language and Knowledge Graph for Multi-hop Reasoning
1 Introduction
2 Related Works
3 Model
3.1 Description

3.2 Framework
3.3 Subgraph Retrieval
3.4 Structural Fusion
3.5 Relation Reasoning
4 Experiments
4.1 Experiment Setup
4.2 Model Comparison
5 Conclusion
References
Commonsense Knowledge Construction with Concept and Pretrained Model
1 Introduction
2 Related Works
3 Methodology
3.1 Framework of CG&BF
3.2 Concept-Based Generator
3.3 BERT-Based Filter
4 Experiments
4.1 Experiment Setup
4.2 Model Comparison
5 Conclusion
References
Simplifying Knowledge-Aware Aggregation for Knowledge Graph Collaborative Filtering
1 Introduction

2 Related Work
3 Task Formulation
4 Methodology
4.1 Personalized Knowledge Aggregation
4.2 User Aggregation
4.3 Prediction Layer
5 Experiments
5.1 Datasets
5.2 Baselines
5.3 Experimental Settings
5.4 Performance Comparison (RQ1)
5.5 Ablation Studies (RQ2)
6 Conclusion
References
Bi-Directional Neighborhood-Aware Network for Entity Alignment in Knowledge Graphs
1 Introduction
2 Related Work
2.1 Embedding-Based Methods
2.2 Phenomenon of Long-Tail
3 Problem Formalization
4 Methodology
4.1 Neighborhood Embedding

4.2 Entity Name Embedding
4.3 Feature Fusion with Bi-attention
4.4 Alignment and Training
5 Experiments
5.1 Experiment Setting
5.2 Main Result
5.3 Ablation Study
5.4 Evaluation by Degrees Interval
5.5 Robustness on Datasets
6 Conclusion
References
SAREM: Semi-supervised Active Heterogeneous Entity Matching Framework
1 Introduction
2 Related Work
2.1 Entity Matching
2.2 EM Based on Active Learning
3 Problem Statement and Definition
4 The Framework: Sarem
4.1 Data Augmentation
4.2 Feature Extraction
4.3 Example Selection