ProjE: Embedding Projection for Knowledge Graph Completion

Abstract

With the large volume of new information created every day, determining the validity of information in a knowledge graph and filling in its missing parts are crucial tasks for many researchers and practitioners. To address this challenge, a number of knowledge graph completion methods have been developed using low-dimensional graph embeddings. Although researchers continue to improve these models using an increasingly complex feature space, we show that simple changes in the architecture of the underlying model can outperform state-of-the-art models without the need for complex feature engineering. In this work, we present a shared variable neural network model called ProjE that fills-in missing information in a knowledge graph by learning joint embeddings of the knowledge graph's entities and edges, and through subtle, but important, changes to the standard loss function. In doing so, ProjE has a parameter size that is smaller than 11 out of 15 existing methods while performing $37\%$ better than the current-best method on standard datasets. We also show, via a new fact checking task, that ProjE is capable of accurately determining the veracity of many declarative statements.

14 pages, Accepted to AAAI 2017

References in corpus (5)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• How to project a bipartite network?
• Computational fact checking from knowledge networks
• Deep Convolutional Ranking for Multilabel Image Annotation
• Locally Adaptive Translation for Knowledge Graph Embedding

Cited by in corpus (40)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• KG-BERT: BERT for Knowledge Graph Completion
• A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
• A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications
• Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework
• An Open-World Extension to Knowledge Graph Completion Models
• Relation Embedding with Dihedral Group in Knowledge Graph
• Neighborhood Mixture Model for Knowledge Base Completion
• Multi-view Knowledge Graph Embedding for Entity Alignment
• Learning beyond datasets: Knowledge Graph Augmented Neural Networks for Natural language Processing
• DOLORES: Deep Contextualized Knowledge Graph Embeddings
• Triple Classification for Scholarly Knowledge Graph Completion
• Open-World Knowledge Graph Completion
• Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study
• Link Prediction using Embedded Knowledge Graphs
• KSR: A Semantic Representation of Knowledge Graph within a Novel Unsupervised Paradigm
• Knowledge Graph Embedding with Atrous Convolution and Residual Learning
• Relation-weighted Link Prediction for Disease Gene Identification
• TechKG: A Large-Scale Chinese Technology-Oriented Knowledge Graph
• A Walk-based Model on Entity Graphs for Relation Extraction
• Augmenting and Tuning Knowledge Graph Embeddings
• Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
• Water Disaggregation via Shape Features based Bayesian Discriminative Sparse Coding
• Distributional Negative Sampling for Knowledge Base Completion
• SCEF: A Support-Confidence-aware Embedding Framework for Knowledge Graph Refinement
• TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
• Representation Learning in Heterogeneous Professional Social Networks with Ambiguous Social Connections
• Embedding Uncertain Knowledge Graphs
• Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder
• SEEK: Segmented Embedding of Knowledge Graphs
• MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning
• Domain Representation for Knowledge Graph Embedding
• PPKE: Knowledge Representation Learning by Path-based Pre-training
• Knowledge Completion for Generics using Guided Tensor Factorization
• Fact Checking via Path Embedding and Aggregation
• Integrating Approaches to Word Representation
• Enriching Medcial Terminology Knowledge Bases via Pre-trained Language Model and Graph Convolutional Network
• Link Prediction on N-ary Relational Data Based on Relatedness Evaluation
• Customized Graph Embedding: Tailoring Embedding Vectors to different Applications