Knowledge Graph Completion with Adaptive Sparse Transfer Matrix

@inproceedings{Ji2016KnowledgeGC,
  title={Knowledge Graph Completion with Adaptive Sparse Transfer Matrix},
  author={Guoliang Ji and Kang Liu and Shizhu He and Jun Zhao},
  booktitle={AAAI},
  year={2016}
}
We model knowledge graphs for their completion by encoding each entity and relation into a numerical space. All previous work including Trans(E, H, R, and D) ignore the heterogeneity (some relations link many entity pairs and others do not) and the imbalance (the number of head entities and that of tail entities in a relation could be different) of knowledge graphs. In this paper, we propose a novel approach TranSparse to deal with the two issues. In TranSparse, transfer matrices are… 
View via Publisher
ojs.aaai.org
276 Citations
Highly Influential Citations
23
Background Citations
84
Methods Citations
92
Results Citations
6

Figures and Tables from this paper

276 Citations

Knowledge Graph Completion for Hyper-relational Data
TLDR
A novel model named TransHR is proposed, which transforms the vectors of hyper-relations between a pair of entities into an individual vector acting as a translation between them, which significantly outperforms Trans(E, H, R) and CTransR especially for hyper-relational data.
Relation path embedding in knowledge graphs
TLDR
This work studies the problem of how to better embed entities and relations of knowledge graphs into different low-dimensional spaces by taking full advantage of the additional semantics of relation paths and proposes a novel relation path embedding model named as RPE.
A Re-Ranking Framework for Knowledge Graph Completion
TLDR
This paper proposes a general-purpose framework which can be employed to improve the performance of knowledge graph completion, and explores the influence of the number of top ranked entities used in the re-ranking phase.
TransMS: Knowledge Graph Embedding for Complex Relations by Multidirectional Semantics
TLDR
This model translates and transmits multidirectional semantics of head/tail entities and relations to tail/head entities with nonlinear functions and the semantics from entities to relations with linear bias vectors, which results in its better scalability in large-scale knowledge graph.
TranS: Transition-based Knowledge Graph Embedding with Synthetic Relation Representation
TLDR
This paper proposes a novel transition-based method, TranS, for knowledge graph embedding, where the single relation vector in traditional scoring patterns is replaced with synthetic relation representation, which can solve issues effectively and efficiently.
CoRelatE: Modeling the Correlation in Multi-fold Relations for Knowledge Graph Embedding
TLDR
A Group-constrained Embedding method which embeds entity nodes and fact nodes from entity space into relation space, restricting the embedded fact nodes related to the same relation to groups with Zero Constrain, Radius Constraint or Cosine Constraints is provided.
A Survey on Knowledge Graph Embedding: Approaches, Applications and Benchmarks
TLDR
This paper systematically introduces the existing state-of-the-art approaches and a variety of applications that benefit from these methods in knowledge graph embedding and introduces the advanced models that utilize additional semantic information to improve the performance of the original methods.
Incorporating Domain and Range of Relations for Knowledge Graph Completion
TLDR
Experimental results show that the TransX\(_C\) method outperforms the corresponding translation-based model, indicating the effectiveness of considering domain and range of relations into link prediction.
Knowledge Graph Embedding for Hyper-Relational Data
TLDR
The novel model TransHR is proposed, which transforms the hyper-relations in a pair of entities into an individual vector, serving as a translation between them, and significantly outperforms Trans (E, H, R) and CTransR, especially for hyperrelational data.
A Novel Asymmetric Embedding Model for Knowledge Graph Completion
TLDR
This paper proposes a novel asymmetrical embedding model (AEM) for knowledge graph completion that weights each dimension of the entity vectors so that it can accurately represent the latent attributes of entities and relationships.
...
...

References

SHOWING 1-10 OF 24 REFERENCES
Knowledge Graph Embedding via Dynamic Mapping Matrix
TLDR
A more fine-grained model named TransD, which is an improvement of TransR/CTransR, which not only considers the diversity of relations, but also entities, which makes it can be applied on large scale graphs.
Learning Entity and Relation Embeddings for Knowledge Graph Completion
TLDR
TransR is proposed to build entity and relation embeddings in separate entity space and relation spaces by first projecting entities from entity space to corresponding relation space and then building translations between projected entities.
Learning to Represent Knowledge Graphs with Gaussian Embedding
TLDR
The experimental results demonstrate that the KG2E method can effectively model the (un)certainties of entities and relations in a KG, and it significantly outperforms state-of-the-art methods (including TransH and TransR).
A latent factor model for highly multi-relational data
TLDR
This paper proposes a method for modeling large multi-relational datasets, with possibly thousands of relations, based on a bilinear structure, which captures various orders of interaction of the data and also shares sparse latent factors across different relations.
Knowledge Graph Embedding by Translating on Hyperplanes
TLDR
This paper proposes TransH which models a relation as a hyperplane together with a translation operation on it and can well preserve the above mapping properties of relations with almost the same model complexity of TransE.
Semantically Smooth Knowledge Graph Embedding
TLDR
The key idea of SSE is to take full advantage of additional semantic information and enforce theembedding space to be semantically smooth, i.e., entities belonging to the same semantic category will lie close to each other in the embedding space.
Translating Embeddings for Modeling Multi-relational Data
TLDR
TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.
Reasoning With Neural Tensor Networks for Knowledge Base Completion
TLDR
An expressive neural tensor network suitable for reasoning over relationships between two entities given a subset of the knowledge base is introduced and performance can be improved when entities are represented as an average of their constituting word vectors.
Learning Structured Embeddings of Knowledge Bases
TLDR
A learning process based on an innovative neural network architecture designed to embed any of these symbolic representations into a more flexible continuous vector space in which the original knowledge is kept and enhanced would allow data from any KB to be easily used in recent machine learning methods for prediction and information retrieval.
A Review of Relational Machine Learning for Knowledge Graphs
TLDR
This paper provides a review of how statistical models can be “trained” on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges in the graph) and how such statistical models of graphs can be combined with text-based information extraction methods for automatically constructing knowledge graphs from the Web.
...
...