Query2box: Reasoning over knowledge graphs in vector space using box embeddings

H Ren, W Hu, J Leskovec - arXiv preprint arXiv:2002.05969, 2020 - arxiv.org
Answering complex logical queries on large-scale incomplete knowledge graphs (KGs) is a
fundamental yet challenging task. Recently, a promising approach to this problem has been …

Knowledge graph embeddings and explainable AI

F Bianchi, G Rossiello, L Costabello… - Knowledge Graphs …, 2020 - ebooks.iospress.nl
Abstract Knowledge graph embeddings are now a widely adopted approach to knowledge
representation in which entities and relationships are embedded in vector spaces. In this …

Convolutional complex knowledge graph embeddings

C Demir, ACN Ngomo - The Semantic Web: 18th International Conference …, 2021 - Springer
We investigate the problem of learning continuous vector representations of knowledge
graphs for predicting missing links. Recent results suggest that using a Hermitian inner …

Benchmark and best practices for biomedical knowledge graph embeddings

D Chang, I Balazevic, C Allen, D Chawla… - arXiv preprint arXiv …, 2020 - arxiv.org
Much of biomedical and healthcare data is encoded in discrete, symbolic form such as text
and medical codes. There is a wealth of expert-curated biomedical domain knowledge …

Bique: Biquaternionic embeddings of knowledge graphs

J Guo, S Kok - arXiv preprint arXiv:2109.14401, 2021 - arxiv.org
Knowledge graph embeddings (KGEs) compactly encode multi-relational knowledge graphs
(KGs). Existing KGE models rely on geometric operations to model relational patterns …

Vector-valued distance and gyrocalculus on the space of symmetric positive definite matrices

F López, B Pozzetti, S Trettel… - Advances in Neural …, 2021 - proceedings.neurips.cc
We propose the use of the vector-valued distance to compute distances and extract
geometric information from the manifold of symmetric positive definite matrices (SPD), and …

Revisiting evaluation of knowledge base completion models

P Pezeshkpour, Y Tian, S Singh - Automated Knowledge Base …, 2020 - par.nsf.gov
Representing knowledge graphs (KGs) by learning embeddings for entities and relations
has led to accurate models for existing KG completion benchmarks. However, due to the …

Hopfe: Knowledge graph representation learning using inverse hopf fibrations

A Bastos, K Singh, A Nadgeri, S Shekarpour… - Proceedings of the 30th …, 2021 - dl.acm.org
Recently, several Knowledge Graph Embedding (KGE) approaches have been devised to
represent entities and relations in a dense vector space and employed in downstream tasks …

Adversarial attacks on knowledge graph embeddings via instance attribution methods

P Bhardwaj, J Kelleher, L Costabello… - arXiv preprint arXiv …, 2021 - arxiv.org
Despite the widespread use of Knowledge Graph Embeddings (KGE), little is known about
the security vulnerabilities that might disrupt their intended behaviour. We study data …

Poisoning knowledge graph embeddings via relation inference patterns

P Bhardwaj, J Kelleher, L Costabello… - arXiv preprint arXiv …, 2021 - arxiv.org
We study the problem of generating data poisoning attacks against Knowledge Graph
Embedding (KGE) models for the task of link prediction in knowledge graphs. To poison …