Multi-modal knowledge graph inference via media convergence and logic rule

Media convergence works by processing information from different modalities and applying them to different domains.It is difficult for the conventional knowledge graph to utilise multi-media features because the introduction of a large amount of information from other modalities reduces the effectiveness of representation learning and makes knowledge graph inference less effective.To address the issue,an inference method based on Media Convergence and Rule-guided Joint Inference model(MCRJI)has been pro-posed.The authors not only converge multi-media features of entities but also introduce logic rules to improve the accuracy and interpretability of link prediction.First,a multi-headed self-attention approach is used to obtain the attention of different media features of entities during semantic synthesis.Second,logic rules of different lengths are mined from knowledge graph to learn new entity representations.Finally,knowledge graph inference is performed based on representing entities that converge multi-media features.Numerous experimental results show that MCRJI outperforms other advanced baselines in using multi-media features and knowledge graph inference,demonstrating that MCRJI provides an excellent approach for knowledge graph inference with converged multi-media features.

Application of graph neural network and feature information enhancement in relation inference of sparse knowledge graph

At present,knowledge embedding methods are widely used in the field of knowledge graph(KG)reasoning,and have been successfully applied to those with large entities and relationships.However,in research and production environments,there are a large number of KGs with a small number of entities and relations,which are called sparse KGs.Limited by the performance of knowledge extraction methods or some other reasons(some common-sense information does not appear in the natural corpus),the relation between entities is often incomplete.To solve this problem,a method of the graph neural network and information enhancement is proposed.The improved method increases the mean reciprocal rank(MRR)and Hit@3 by 1.6%and 1.7%,respectively,when the sparsity of the FB15K-237 dataset is 10%.When the sparsity is 50%,the evaluation indexes MRR and Hit@10 are increased by 0.8%and 1.8%,respectively.

Paleobiogeographic Knowledge Graph:An Ongoing Work with Fundamental Support for Future Research

Paleobiogeography investigates geographical distributions of fossil organisms and controlling factors that affect their distributions in geological history,to reveal the macro-evolution and coordinated development of life and the environment.It is a crucial window for understanding the biosphere and the geographical environment.After two centuries of development,paleobiogeographic studies have led to the accumulation of significant amounts of knowledge and data;however,the voluminous outputs present the characteristics of an“isolated island”with a scattered,limited number of authoritative definitions of terminologies and semantic heterogeneity among them.This makes data queries cumbersome,the rate of data reuse low,and data sharing more difficult.A knowledge graph(KG)has the advantage of expressing concepts and their semantic relations,which is an important tool for achieving data organization and fusion,and data mining;further,it is also a key technology for realizing the unrestricted sharing of paleobiogeographic information.Through our efforts over the past two years,a paleobiogeographic KG was developed based on the established construction procedure of the KG,which contains 273 concepts,172 properties,and 47 rules.Meanwhile,the completion of this KG and the construction of a paleobiogeographic platform for display and analysis are now being carried out.