Holographic Embeddings of Knowledge Graphs
Голографические вложения графов знаний
2016-03-02
SCID: 54.1/rf3g7egq
Discuss with AI
circular correlationholographic embeddingsknowledge graphslink predictionrelational learning
Figures from the paper
Abstract (AI)
Learning embeddings of entities and relations is an efficient and versatile method to perform machine learning on relational data such as knowledge graphs. In this work, we propose holographic embeddings (HolE) to learn compositional vector space representations of entire knowledge graphs. The proposed method is related to holographic models of associative memory in that it employs circular correlation to create compositional representations. By using correlation as the compositional operator, HolE can capture rich interactions but simultaneously remains efficient to compute, easy to train, and scalable to very large datasets. Experimentally, we show that holographic embeddings are able to outperform state-of-the-art methods for link prediction on knowledge graphs and relational learning benchmark datasets.
Key Findings
1
Experiments show that HolE outperforms state-of-the-art methods on knowledge-graph link prediction and relational-learning benchmarks.
2
HolE uses circular correlation as its composition operator, enabling rich interactions between entity and relation representations.
3
Holographic Embeddings (HolE) learn compositional vector representations for entire knowledge graphs.
4
The method remains computationally efficient, easy to train, and scalable to very large datasets.
Research Object
Knowledge graphs (entities and relations represented for relational learning)
Research Subject
the effectiveness, expressive capacity, computational efficiency, trainability, scalability, and link-prediction performance of holographic embeddings for compositional representation of knowledge graphs
Publication Details
Publication Date
2016-03-02
Journal
Publisher
ISSN
Cited by
559
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai3
Cited by10
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications2021
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge2017
Knowledge Graph Embedding: A Survey of Approaches and Applications2017
Convolutional 2D Knowledge Graph Embeddings2018
Knowledge Graphs2021
Knowledge Graph Embedding for Link Prediction: A Comparative Analysis2021
Knowledge Graphs: Opportunities and Challenges2023
Knowledge Graph Completion: A Review2020
A Re-evaluation of Knowledge Graph Completion Methods2020
Triple Classification for Scholarly Knowledge Graph Completion2021