Knowledge Graph Embedding for Link Prediction: A Comparative Analysis

Abstract

Knowledge Graphs (KGs) have found many applications in industry and academic settings, which in turn, have motivated considerable research efforts towards large-scale information extraction from a variety of sources. Despite such efforts, it is well known that even state-of-the-art KGs suffer from incompleteness. Link Prediction (LP), the task of predicting missing facts among entities already a KG, is a promising and widely studied task aimed at addressing KG incompleteness. Among the recent LP techniques, those based on KG embeddings have achieved very promising performances in some benchmarks. Despite the fast growing literature in the subject, insufficient attention has been paid to the effect of the various design choices in those methods. Moreover, the standard practice in this area is to report accuracy by aggregating over a large number of test facts in which some entities are over-represented; this allows LP methods to exhibit good performance by just attending to structural properties that include such entities, while ignoring the remaining majority of the KG. This analysis provides a comprehensive comparison of embedding-based LP methods, extending the dimensions of analysis beyond what is commonly available in the literature. We experimentally compare effectiveness and efficiency of 16 state-of-the-art methods, consider a rule-based baseline, and report detailed analysis over the most popular benchmarks in the literature.

arXiv commentAndrea Rossi, Donatella Firmani, Antonio Matinata, Paolo Merialdo, Denilson Barbosa. 2020. Knowledge Graph Embedding for Link Prediction: A Comparative Analysis. In ACM Transactions on Knowledge Discovery from Data. January 2021. (TKDD 2021). ACM, New York, NY, USA

References in corpus (3)

• A Review of Relational Machine Learning for Knowledge Graphs
• Interaction Embeddings for Prediction and Explanation in Knowledge Graphs
• STransE: a novel embedding model of entities and relationships in knowledge bases

Cited by in corpus (37)

• Multi-Modal Knowledge Graph Construction and Application: A Survey
• A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
• Knowledge Graph Reasoning with Relational Digraph
• Understanding the Performance of Knowledge Graph Embeddings in Drug Discovery
• Recommender systems based on graph embedding techniques: A comprehensive review
• Relational Graph Convolutional Networks: A Closer Look
• Comprehensible Artificial Intelligence on Knowledge Graphs: A survey
• Knowledge Graphs in Practice: Characterizing their Users, Challenges, and Visualization Opportunities
• Reinforced Anytime Bottom Up Rule Learning for Knowledge Graph Completion
• Toward Degree Bias in Embedding-Based Knowledge Graph Completion
• Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks
• Knowledge-based Entity Prediction for Improved Machine Perception in Autonomous Systems
• DRExplainer: Quantifiable Interpretability in Drug Response Prediction with Directed Graph Convolutional Network
• LogicRec: Recommendation with Users' Logical Requirements
• Event Prediction using Case-Based Reasoning over Knowledge Graphs
• Utilising Graph Machine Learning within Drug Discovery and Development
• Predicting Drug-Drug Interactions Using Heterogeneous Graph Neural Networks: HGNN-DDI
• A Survey of Knowledge Graph Embedding and Their Applications
• SAFRAN: An interpretable, rule-based link prediction method outperforming embedding models
• Predicting affinity ties in a surname network
• Efficient Relation-aware Scoring Function Search for Knowledge Graph Embedding
• Morescient GAI for Software Engineering (Extended Version)
• Dynamic Relation Repairing for Knowledge Enhancement
• Integrating multi-type aberrations from DNA and RNA through dynamic mapping gene space for subtype-specific breast cancer driver discovery
• Prediction of Adverse Biological Effects of Chemicals Using Knowledge Graph Embeddings
• Reproducibility and Artifact Consistency of the SIGIR 2022 Recommender Systems Papers Based on Message Passing
• Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis
• OWL2Vec*: Embedding of OWL Ontologies
• KSG: Knowledge and Skill Graph
• Reevaluation of Inductive Link Prediction
• Adaptive Similarity Function with Structural Features of Network Embedding for Missing Link Prediction
• DynACPD Embedding Algorithm for Prediction Tasks in Dynamic Networks
• Variational Quantum Models for Knowledge Graph Embeddings on NISQ Devices
• Implications of Topological Imbalance for Representation Learning on Biomedical Knowledge Graphs
• Thematic recommendations on knowledge graphs using multilayer networks
• Scalable and interpretable rule-based link prediction for large heterogeneous knowledge graphs
• Inductive Link Prediction on N-ary Relational Facts via Semantic Hypergraph Reasoning