SimplE Embedding for Link Prediction in Knowledge Graphs

Abstract

Knowledge graphs contain knowledge about the world and provide a structured representation of this knowledge. Current knowledge graphs contain only a small subset of what is true in the world. Link prediction approaches aim at predicting new links for a knowledge graph given the existing links among the entities. Tensor factorization approaches have proved promising for such link prediction problems. Proposed in 1927, Canonical Polyadic (CP) decomposition is among the first tensor factorization approaches. CP generally performs poorly for link prediction as it learns two independent embedding vectors for each entity, whereas they are really tied. We present a simple enhancement of CP (which we call SimplE) to allow the two embeddings of each entity to be learned dependently. The complexity of SimplE grows linearly with the size of embeddings. The embeddings learned through SimplE are interpretable, and certain types of background knowledge can be incorporated into these embeddings through weight tying. We prove SimplE is fully expressive and derive a bound on the size of its embeddings for full expressivity. We show empirically that, despite its simplicity, SimplE outperforms several state-of-the-art tensor factorization techniques. SimplE's code is available on GitHub at https://github.com/Mehran-k/SimplE.

arXiv commentAccepted for publication at conference on neural information processing systems (NIPS 2018). 12 pages, 2 figure, 2 tables, 5 propositions

Cited by in corpus (35)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Knowledge Graphs
• A Survey of Fake News: Fundamental Theories, Detection Methods, and Opportunities
• A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
• Hypernetwork Knowledge Graph Embeddings
• Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure
• A Review of Knowledge Graph Completion
• Knowledge Graph informed Fake News Classification via Heterogeneous Representation Ensembles
• Relation Embedding with Dihedral Group in Knowledge Graph
• Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
• Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition
• The Survey on Multi-Source Data Fusion in Cyber-Physical-Social Systems:Foundational Infrastructure for Industrial Metaverses and Industries 5.0
• Ultrahyperbolic Knowledge Graph Embeddings
• LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction
• Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models
• Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completion
• Triple Classification for Scholarly Knowledge Graph Completion
• Knowledge Graph Embeddings and Explainable AI
• SAppKG: Mobile App Recommendation Using Knowledge Graph and Side Information-A Secure Framework
• Adaptive Attentional Network for Few-Shot Knowledge Graph Completion
• Optimizing DNN Compilation for Distributed Training with Joint OP and Tensor Fusion
• Knowledge Base Completion: Baseline strikes back (Again)
• Joint Embedding Learning of Educational Knowledge Graphs
• Reasoning on Knowledge Graphs with Debate Dynamics
• NQE: N-ary Query Embedding for Complex Query Answering over Hyper-Relational Knowledge Graphs
• From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
• Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes
• Dynamic Relation Repairing for Knowledge Enhancement
• NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural Architecture Search
• Binarized Knowledge Graph Embeddings
• RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion
• Current Challenges and Future Directions in Podcast Information Access
• SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods
• CEAR: Cross-Entity Aware Reranker for Knowledge Base Completion
• Principled Representation Learning for Entity Alignment