Knowledge Transfer for Out-of-Knowledge-Base Entities : A Graph Neural Network Approach

By Takuo Hamaguchi, Hidekazu Oiwa, Masashi Shimbo, Yuji Matsumoto. 2017

379 citations recorded by the source corpus.

Knowledge base completion (KBC) aims to predict missing information in a knowledge this http URL this paper, we address the out-of-knowledge-base (OOKB) entity problem in KBC:how to answer queries concerning test entities not observed at training time. Existing embedding-based KBC models assume that all test entities are available at training time, making it unclear how to obtain embeddings for new entities without costly retraining. To solve the OOKB entity problem without retraining, we use graph neural networks (Graph-NNs) to compute the embeddings of OOKB entities, exploiting the limited auxiliary knowledge provided at test time.The experimental results show the effectiveness of our proposed model in the OOKB setting.Additionally, in the standard KBC setting in which OOKB entities are not involved, our model achieves state-of-the-art performance on the WordNet dataset. The code and dataset are available at this https URL

Subfields: Artificial Intelligence, Management Science and Operations Research

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

In Management Science and Operations Research

Citations in the corpus

Relational inductive biases, deep learning, and graph networks (2018, background): “…(Sukhbaatar et al., 2016; Hoshen, 2017; Kipf et al., 2018), to reason about knowledge graphs (Bordes et al., 2013; O˜noro-Rubio et al., 2017; Hamaguchi et al., 2017), to predict the chemical properties of molecules (Duvenaud et al., 2015; Gilmer et al., 2017), to predict traﬃc on roads (Li…”
Knowledge Infused Learning (K-IL): Towards Deep Incorporation of Knowledge in Deep Learning (2019, background): “D kg and Seeded-KG represent two knowledge structures requiring a process of transferring the knowledge from one structure to another (Hamaguchi et al. 2017).”
Permutation Invariant Graph Generation via Score-Based Generative Modeling (2020, methodology): “Graphs are used to capture relational structure in many domains, including knowledge bases (Hamaguchi et al., 2017), social networks (Hamilton et al.”
Graph Neural Networks in Recommender Systems: A Survey (2020, background): “Recently, systems based on variants of GNN have demonstrated ground-breaking performance on many tasks related to graph data, such as physical systems [2, 45], protein structure [11], knowledge graph [15] and other areas [3, 4, 26].”
Graph Neural Networks: A Review of Methods and Applications (2018, background): “graphs can be used as denotation of a large number of systems across various areas including social science (social networks) [1], [2], natural science (physical systems [3], [4] and protein-protein interaction networks [5]), knowledge graphs [6] and many other research areas [7].”
Inductive Relation Prediction by Subgraph Reasoning (2019, background): “, 2019) and (Hamaguchi et al., 2017) learn to generate embeddings for unseen nodes by aggregating neighboring node embeddings using GNNs.”
AliGraph: A Comprehensive Graph Neural Network Platform (2019, background): “Typical examples include social networks [21, 30], physical systems [1, 43], biological networks [14], knowledge graphs [19] and etc [28].”
Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information (2020, background): “Graph neural networks (GNNs), which generalize neural networks for graph structured data, have shown great success for various applications [2, 18, 26, 47, 50, 51].”
Text Level Graph Neural Network for Text Classification (2019, background): “While many tasks in reality such as knowledge graphs (Hamaguchi et al., 2017), social networks (Hamilton et al.”