Locally Adaptive Translation for Knowledge Graph Embedding

By Yantao Jia, Yuanzhuo Wang, Hailun Lin, Xiaolong Jin, Xueqi Cheng. 2015

94 citations recorded by the source corpus.

Knowledge graph embedding aims to represent entities and relations in a large-scale knowledge graph as elements in a continuous vector space. Existing methods, e.g., TransE and TransH, learn embedding representation by defining a global margin-based loss function over the data. However, the optimal loss function is determined during experiments whose parameters are examined among a closed set of candidates. Moreover, embeddings over two knowledge graphs with different entities and relations share the same set of candidate loss functions, ignoring the locality of both graphs. This leads to the limited performance of embedding related applications. In this paper, we propose a locally adaptive translation method for knowledge graph embedding, called TransA, to find the optimal loss function by adaptively determining its margin over different knowledge graphs. Experiments on two benchmark data sets demonstrate the superiority of the proposed method, as compared to the-state-of-the-art ones.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tim Weninger
2. Baoxu Shi
3. Carlo Zaniolo
4. Muhao Chen
5. Mohan Yang
6. Yingtao Tian
7. Wei Hu
8. Zequn Sun

Citations in the corpus

• A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, neutral): “TransA [130] khþ r tk”
• ProjE: Embedding Projection for Knowledge Graph Completion (2016, background): “Unlike aforementioned models that focus on different E ( h, r, t ) , TransA [19] introduces an adaptive local margin approach that determines γ by a closed set of entity candidates.”
• Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment (2016, methodology): “Like previous works [ Bordes et al. , 2013; Wang et al. , 2014; Jia et al. , 2016 ] , for each language version, 10% triples are selected as the test set, and the remaining becomes the training set.”