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

Abstract

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 proposed. 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.

Data Element Sharing in Convergence Media Ecology Based on Evolutionary Game

“…Wang states that the proportion of traditional media and new media in the field of news has changed significantly, and in order to achieve sustainable development, media should innovate and optimize their business philosophy and mode of operation, improve the theoretical and practical level of news editing, use modern consciousness to edit news, and achieve their own progress through integration and innovation [47]. Lin et al explain that media convergence involves processing information from different sources and applying it to various domains, but conventional knowledge graphs struggle with multimedia features due to the introduction of extensive cross-modal information, which diminishes representation learning effectiveness and knowledge graph inference; they introduced a remedy through their Media Convergence and Rule-guided Joint Inference model (MCRJI) [48].…”