Temporal knowledge graph embedding via sparse transfer matrix

TL;DR: A comprehensive review of TKGC methods and their details is provided, which focuses on continuous TKGs and predicts future events, and then classifies all extrapolation methods based on the algorithms they utilize.

TL;DR: A multisource hierarchical neural network (MSHE) is proposed for knowledge graph embedding, efficiently extracting complex graph information and integrating heterogeneous entities and relations, outperforming state-of-the-art baselines on FB15k-237, YAGO3-10, and WN18RR datasets.

TL;DR: This paper introduces a distribution-based representation of Knowledge Quality (KQ) using the congruence between knowledge pieces from varied sources, quantifying uncertainty and credibility, and proposes an iterative method to update KQ, with experimental studies demonstrating its effectiveness.

TL;DR: This study proposes ILR-IR, a hybrid model combining embedding-based and logical rule-based methods for temporal knowledge graph extrapolation, offering interpretable insights and superior performance in predicting future events with robust zero-shot reasoning abilities.

TL;DR: This chapter discusses methods related to the normal equations of linear algebra, and some of the techniques used in this chapter were derived from previous chapters of this book.

TL;DR: This volume contains the papers accepted to the 25th International Conference on Machine Learning (ICML 2008), the annual conference of the International Machine Learning Society, and provides a venue for the presentation and discussion of current research in the field of machine learning.

TL;DR: This paper proposes TransH which models a relation as a hyperplane together with a translation operation on it and can well preserve the above mapping properties of relations with almost the same model complexity of TransE.