Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding
06 Jul 2022
TL;DR: In this article , the authors propose a model MorsE, which does not learn embeddings for entities but learns transferable meta-knowledge that can be used to produce entity embedding.
read more
Abstract: Knowledge graphs (KGs) consisting of a large number of triples have become widespread recently, and many knowledge graph embedding (KGE) methods are proposed to embed entities and relations of a KG into continuous vector spaces. Such embedding methods simplify the operations of conducting various in-KG tasks (e.g., link prediction) and out-of-KG tasks (e.g., question answering). They can be viewed as general solutions for representing KGs. However, existing KGE methods are not applicable to inductive settings, where a model trained on source KGs will be tested on target KGs with entities unseen during model training. Existing works focusing on KGs in inductive settings can only solve the inductive relation prediction task. They can not handle other out-of-KG tasks as general as KGE methods since they don't produce embeddings for entities. In this paper, to achieve inductive knowledge graph embedding, we propose a model MorsE, which does not learn embeddings for entities but learns transferable meta-knowledge that can be used to produce entity embeddings. Such meta-knowledge is modeled by entity-independent modules and learned by meta-learning. Experimental results show that our model significantly outperforms corresponding baselines for in-KG and out-of-KG tasks in inductive settings.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Disentangled Ontology Embedding for Zero-shot Learning
Yuxia Geng,Jiaoyan Chen,Wen Zhang,Yajing Xu,Zhuo Chen,Jeff Z. Pan,Yufen Huang,Feiyu Xiong,Hua-zeng Chen +8 more
- 08 Jun 2022
TL;DR: This paper proposes to learn disentangled ontology embeddings guided by ontology properties to capture and utilize more fine-grained class relationships in different aspects of Zero-shot Learning.
MINES: Message Intercommunication for Inductive Relation Reasoning over Neighbor-Enhanced Subgraphs
Kenny Ye Liang,Lingyuan Meng,Sihang Zhou,Wenxuan Tu,Siwei Wang,Yue Liu,Meng Liu,Long Zhao,Xiangjun Dong,Xinwang Liu +9 more
- 24 Mar 2024
TL;DR: MINES, a novel GraIL-based framework, addresses limitations in inductive relation reasoning by introducing a message intercommunication mechanism on neighbor-enhanced subgraphs, capturing hidden mutual information and enhancing information collection for knowledge graph reasoning tasks.
24
Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings
Peng Wang,Xin Xie,Xiaohan Wang,Ninyu Zhang +3 more
TL;DR: KNN-KGE is a knowledge graph embedding approach that explicitly memorizes rare or emerging entities by interpolating their distribution with k-nearest neighbors.
11
Improving deep learning with prior knowledge and cognitive models: A survey on enhancing interpretability, adversarial robustness and zero-shot learning
TL;DR: This survey reviews knowledge-informed and brain-inspired cognitive systems for enhancing deep learning's interpretability, adversarial robustness, and zero-shot learning capabilities, leveraging prior knowledge and cognitive models to improve performance and explainability.
6
A survey of inductive knowledge graph completion
Xinyu Liang,Guannan Si,Jianxin Li,Pengxin Tian,Zhaoliang An,Fengyu Zhou +5 more
- 13 Dec 2023
TL;DR: This paper is the first one that provides a comprehensive review of IKGC from both technical and theoretical perspectives and divided into two groups: structural information-based IKGC and additional information-based IKGC.
6
References
Freebase: a collaboratively created graph database for structuring human knowledge
Kurt Bollacker,Colin Evans,Praveen Paritosh,Tim Sturge,Jamie Taylor +4 more
- 09 Jun 2008
TL;DR: MQL provides an easy-to-use object-oriented interface to the tuple data in Freebase and is designed to facilitate the creation of collaborative, Web-based data-oriented applications.
6.1K
•Posted Content
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
TL;DR: ConceptNet as discussed by the authors is a knowledge graph that connects words and phrases of natural language with labeled edges to represent the general knowledge involved in understanding language, improving natural language applications by allowing the application to better understand the meanings behind the words people use.
Knowledge Graph Embedding: A Survey of Approaches and Applications
TL;DR: This article provides a systematic review of existing techniques of Knowledge graph embedding, including not only the state-of-the-arts but also those with latest trends, based on the type of information used in the embedding task.
2.8K
•Proceedings Article
Toward an architecture for never-ending language learning
Andrew Carlson,Justin Betteridge,Bryan Kisiel,Burr Settles,Estevam R. Hruschka,Tom M. Mitchell +5 more
- 11 Jul 2010
TL;DR: This work proposes an approach and a set of design principles for an intelligent computer agent that runs forever and describes a partial implementation of such a system that has already learned to extract a knowledge base containing over 242,000 beliefs.
•Posted Content
Convolutional 2D Knowledge Graph Embeddings
TL;DR: ConvE as discussed by the authors is a multi-layer convolutional network model for link prediction, which achieves state-of-the-art results on several established datasets, such as Freebase and YAGO3.
1.8K