• Corpus ID: 239998166

Standing on the Shoulders of Predecessors: Meta-Knowledge Transfer for Knowledge Graphs

@article{Chen2021StandingOT,
  title={Standing on the Shoulders of Predecessors: Meta-Knowledge Transfer for Knowledge Graphs},
  author={Mingyang Chen and Wen Zhang and Yushan Zhu and Hongting Zhou and Zonggang Yuan and Changliang Xu and Huajun Chen},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.14170}
}
Knowledge graphs (KGs) have become widespread, and various knowledge graphs are constructed incessantly to support many in-KG and out-of-KG applications. During the construction of KGs, although new KGs may contain new entities with respect to constructed KGs, some entity-independent knowledge can be transferred from constructed KGs to new KGs. We call such knowledge meta-knowledge, and refer to the problem of transferring meta-knowledge from constructed (source) KGs to new (target) KGs to… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 57 REFERENCES
Automated Relational Meta-learning
TLDR
An automated relational meta-learning (ARML) framework that automatically extracts the cross-task relations and constructs the meta-knowledge graph is proposed and the results demonstrate the superiority of ARML over state-of-the-art baselines.
One-Shot Relational Learning for Knowledge Graphs
TLDR
This work proposes a one-shot relational learning framework, which utilizes the knowledge distilled by embedding models and learns a matching metric by considering both the learned embeddings and one-hop graph structures.
Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs
TLDR
This work proposes a Meta Relational Learning (MetaR) framework to do the common but challenging few-shot link prediction in KGs, namely predicting new triples about a relation by only observing a few associative triples.
Knowledge Graph Embedding: A Survey of Approaches and Applications
TLDR
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.
Few-Shot Knowledge Graph Completion
TLDR
This work proposes a novel few-shot relation learning model (FSRL) that can effectively capture knowledge from heterogeneous graph structure, aggregate representations of few- shot references, and match similar entity pairs of reference set for every relation.
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
TLDR
This paper proposes a textual inference framework for answering commonsense questions, which effectively utilizes external, structured commonsense knowledge graphs to perform explainable inferences.
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
TLDR
This work proposes a new model, QA-GNN, which addresses the problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) through two key innovations: relevance scoring and joint reasoning.
Interaction Embeddings for Prediction and Explanation in Knowledge Graphs
TLDR
It is shown experimentally that CrossE, benefiting from interaction embeddings, is more capable of generating reliable explanations to support its predictions, and achieves state-of-the-art results on complex and more challenging datasets.
Modeling Relational Data with Graph Convolutional Networks
TLDR
It is shown that factorization models for link prediction such as DistMult can be significantly improved through the use of an R-GCN encoder model to accumulate evidence over multiple inference steps in the graph, demonstrating a large improvement of 29.8% on FB15k-237 over a decoder-only baseline.
Fine-Grained Evaluation of Rule- and Embedding-Based Systems for Knowledge Graph Completion
TLDR
This work presents a fine-grained evaluation that gives insight into characteristics of the most popular datasets and points out the different strengths and shortcomings of the examined approaches, and combines both families of approaches via ensemble learning.
...
1
2
3
4
5
...