GAKE: Graph Aware Knowledge Embedding

By Jun Feng, Minlie Huang, Yang Yang, Xiaoyan Zhu. 2016

92 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, background): “[41], [42] O min(station, company),O ð2Þ min(station, role),O ð2Þ min(destination, boarding) PLE [84] Orank(mention-type) +O min(mention, feature) + O ð2Þ min(type, type) IONE [26] O min(node, node) +O(anchor align) HEBE [45] O min(node, other nodes in one hyperedge) GAKE [38] Oð2Þ max(node, neighbo”
KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings (2018, methodology): “Graph embedding has provided the representational flexibility for neural models in many NLP tasks, such as dialog system [He et al., 2017], question answering [Zhang et al., 2017], link prediction [Bordes et al., 2013] and triple classification [Feng et al., 2016].”
Network Representation Learning: A Survey (2017, background): “For example, knowledge graph completion intends to discover complete relationships between entities, and a recent work [85] has proposed to use graph context to find missing links between entities.”
SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions (2016, background): “Similar researches include TransG (Xiao, Huang, and Zhu 2016b), TransD (Ji et al. ), (Feng et al. 2016) and TransM (Fan et al. 2014).”
Attention Models in Graphs (2018, methodology): “A number of work have been proposed to study graph attention for node-level tasks, the most notable of which are node classification and link prediction [Abu-El-Haija et al. 2017; Feng et al. 2016; Han et al. 2018; Thekumparampil et al. 2018; Velickovic et al. 2018; Zhao et al. 2017].”
Knowledge Graph Embedding: A Survey of Approaches and Applications (2017, background): “[119] proposed a graphaware embedding model which learns entity and relation representations by leveraging three types of graph structures.”
Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation (2019, background): “Incorporating attention mechanism to effectively handle graph-like data has become popular in recent years [17, 12, 23, 22, 4].”