SimplE Embedding for Link Prediction in Knowledge Graphs
Explore this paper's citation graph
Summary
It is proved SimplE is fully expressive and derive a bound on the size of its embeddings for full expressivity and shown empirically that, despite its simplicity, SimplE outperforms several state-of-the-art tensor factorization techniques.
- Type
- preprint
- Published
- 2018-02-13
- Cited by
- 869
- References
- 69
- Access
- Open access
- OpenAlex
- https://openalex.org/W2785761199
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:3674966
Keywords
Simple (philosophy), Embedding, Computer science, Theoretical computer science, Link (geometry)
References
- ProbLog: A Probabilistic Prolog and its Application in Link Discovery
- A short introduction to probabilistic soft logic
- A Three-Way Model for Collective Learning on Multi-Relational Data
- Modeling Relation Paths for Representation Learning of Knowledge Bases
- Toward an Architecture for Never-Ending Language Learning
- A Review of Relational Machine Learning for Knowledge Graphs
- Embedding Entities and Relations for Learning and Inference in Knowledge Bases
- Introduction to Statistical Relational Learning
- Random Walk Inference and Learning in A Large Scale Knowledge Base
- Introduction to statistical relational learning
- Incremental Knowledge Base Construction Using DeepDive
- Lifted graphical models: a survey
- Approximation capabilities of multilayer feedforward networks
- Fast query execution for retrieval models based on path-constrained random walks
- Knowledge vault: a web-scale approach to probabilistic knowledge fusion
- Relational retrieval using a combination of path-constrained random walks
- WordNet: A Lexical Database for English
- Freebase: a collaboratively created graph database for structuring human knowledge
- Factorizing YAGO: scalable machine learning for linked data
- Approximation by superpositions of a sigmoidal function
Cited by
- An overview of embedding models of entities and relationships for knowledge base completion
- From Knowledge Graph Embedding to Ontology Embedding? An Analysis of the Compatibility between Vector Space Representations and Rules
- Improved Knowledge Graph Embedding using Background Taxonomic Information
- A Relational Tucker Decomposition for Multi-Relational Link Prediction
- TuckER: Tensor Factorization for Knowledge Graph Completion
- Level-2 node clustering coefficient-based link prediction
- Representing and learning relations and properties under uncertainty
- AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
- MDE: Multiple Distance Embeddings for Link Prediction in Knowledge Graphs
- Knowledge Hypergraphs: Extending Knowledge Graphs Beyond Binary Relations
- Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey
- Relation Embedding with Dihedral Group in Knowledge Graph
- Binarized Knowledge Graph Embeddings
- Unsupervised Adversarial Graph Alignment with Graph Embedding
- Diachronic Embedding for Temporal Knowledge Graph Completion
- Time2Vec: Learning a Vector Representation of Time
- Distantly Supervised Biomedical Knowledge Acquisition via Knowledge Graph Based Attention
- Drug-Drug Interaction Prediction Based on Knowledge Graph Embeddings and Convolutional-LSTM Network
- Online Knowledge Learning Model Based on Gravitational Field Theory
- Anytime Bottom-Up Rule Learning for Knowledge Graph Completion