8,398 Hits in 5.2 sec

Query Embedding on Hyper-relational Knowledge Graphs [article]

Dimitrios Alivanistos and Max Berrendorf and Michael Cochez and Mikhail Galkin
2022 arXiv   pre-print
Building upon recent advancements in Graph Neural Networks and query embedding techniques, we study how to embed and answer hyper-relational conjunctive queries.  ...  Multi-hop logical reasoning is an established problem in the field of representation learning on knowledge graphs (KGs).  ...  HYPER-RELATIONAL KNOWLEDGE GRAPHS AND QUERIES Definition 3.1 (Hyper-relational Knowledge Graph). Given a finite set of entities E, and a finite set of relations R, let Q = 2 (R×E) .  ... 
arXiv:2106.08166v3 fatcat:xaedvxacwnflphts4nw66wvvri

TransHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction [article]

Yizhi Li, Wei Fan, Chao Liu, Chenghua Lin, Jiang Qian
2022 arXiv   pre-print
Knowledge graph embedding methods are important for knowledge graph completion (link prediction) due to their robust performance and efficiency on large-magnitude datasets.  ...  One state-of-the-art method, PairRE, leverages two separate vectors for relations to model complex relations (i.e., 1-to-N, N-to-1, and N-to-N) in knowledge graphs.  ...  RELATED WORK Knowledge graph embedding methods are proposed to model the intrinsic properties of facts and to conduct knowledge graph completion.  ... 
arXiv:2204.13221v1 fatcat:gjwqwbc4snfblas5m6mvx5jy2m

Few-Shot Semantic Relation Prediction across Heterogeneous Graphs [article]

Pengfei Ding, Yan Wang, Guanfeng Liu, Xiaofang Zhou
2022 arXiv   pre-print
Since a variety of semantic relations exist in multiple heterogeneous graphs, the transferable knowledge can be mined from some existing semantic relations to help predict the new semantic relations with  ...  Thirdly, using the well-initialized two-view graph neural network and hyper-prototypical network, MetaGS can effectively learn new semantic relations from different graphs while overcoming the limitation  ...  Hyper-GNN. After constructing the hyper-graph G hyper , we adopt an attention-based GNN on G hyper to learn the prototype of the semantic relation class.  ... 
arXiv:2207.05068v1 fatcat:awbc6tiyefanbnp7lo7bozdaom

Incorporating Connections Beyond Knowledge Embeddings: A Plug-and-Play Module to Enhance Commonsense Reasoning in Machine Reading Comprehension [article]

Damai Dai, Hua Zheng, Zhifang Sui, Baobao Chang
2021 arXiv   pre-print
Beyond enriching word representations with knowledge embeddings, PIECER constructs a joint query-passage graph to explicitly guide commonsense reasoning by the knowledge-oriented connections between words  ...  Previous methods tackle this problem by enriching word representations via pre-trained Knowledge Graph Embeddings (KGE).  ...  For PIECER, we tune hyper-parameters on the development set.  ... 
arXiv:2103.14443v1 fatcat:cnmfvwdfe5e4pb5hgwldjrn3dq

A Quaternion-embedded Capsule Network Model for Knowledge Graph Completion

Heng Chen, Weimei Wang, Guanyu Li, Yimin Shi
2020 IEEE Access  
Based on these characteristics of quaternions, we use the embeddings of entities and relations trained from QuaR as the input to CapS-QuaR model.  ...  Experimental results on multiple benchmark knowledge graphs show that the proposed method is not only scalable, but also able to predict the correctness of triples in knowledge graphs and significantly  ...  of the knowledge graph completion. • In addition, we also propose a knowledge graph embedding model QuaR that uses the quaternion as a relational rotation.  ... 
doi:10.1109/access.2020.2997177 fatcat:tmmbgi7cmvfk7pdguklrqmcwoq

Message Passing for Hyper-Relational Knowledge Graphs [article]

Mikhail Galkin, Priyansh Trivedi, Gaurav Maheshwari, Ricardo Usbeck, Jens Lehmann
2020 arXiv   pre-print
Hyper-relational knowledge graphs (KGs) (e.g., Wikidata) enable associating additional key-value pairs along with the main triple to disambiguate, or restrict the validity of a fact.  ...  In this work, we propose a message passing based graph encoder - StarE capable of modeling such hyper-relational KGs.  ...  Through our experiments (Sec. 6), we find that STARE based model generally outperforms other approaches on the task of link prediction (LP) over hyper-relational knowledge graphs.  ... 
arXiv:2009.10847v1 fatcat:cuicoygdzvc6pc2sytjdbeo7z4

Approximate Knowledge Graph Query Answering: From Ranking to Binary Classification [chapter]

Ruud van Bakel, Teodor Aleksiev, Daniel Daza, Dimitrios Alivanistos, Michael Cochez
2021 Lecture Notes in Computer Science  
A special case of the aforementioned phenomenon can be seen in knowledge graphs, where this mostly appears in the form of missing or incorrect edges and nodes.Structured querying on such incomplete graphs  ...  To solve this, we introduce Message Passing Query Boxes (MPQB), which takes binary classification metrics back into use and shows the effect this has on the recently proposed query embedding method MPQE  ...  Approximate Query Answering on Knowledge Graphs We define a knowledge graph as a tuple G = (V, R, E), where V is a set of entities, R a set of relation types, and E a set of binary predicates of the form  ... 
doi:10.1007/978-3-030-72308-8_8 fatcat:4r2tnxh4kfalvekgfmcjwfgsem

Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings [article]

Hongyu Ren, Weihua Hu, Jure Leskovec
2020 arXiv   pre-print
Answering complex logical queries on large-scale incomplete knowledge graphs (KGs) is a fundamental yet challenging task.  ...  Our main insight is that queries can be embedded as boxes (i.e., hyper-rectangles), where a set of points inside the box corresponds to a set of answer entities of the query.  ...  While our work is also based on box embeddings we employ them for logical reasoning in massive heterogeneous knowledge graphs.  ... 
arXiv:2002.05969v2 fatcat:m533aorzare75oi22aug4bbh2i

Self-attention Presents Low-dimensional Knowledge Graph Embeddings for Link Prediction [article]

Peyman Baghershahi, Reshad Hosseini, Hadi Moradi
2022 arXiv   pre-print
A few models have tried to tackle the link prediction problem, also known as knowledge graph completion, by embedding knowledge graphs in comparably lower dimensions.  ...  We utilize a large number of self-attention heads as the key to applying query-dependent projections to capture mutual information between entities and relations.  ...  A knowledge graph KG is a subset of all possible true triples. Formally, each entity and relation in KG is associated with an embedding vector.  ... 
arXiv:2112.10644v2 fatcat:t2w2rz7c65ayfm7yx6rmvu2wgy

Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations [article]

Yihong Chen, Pasquale Minervini, Sebastian Riedel, Pontus Stenetorp
2021 arXiv   pre-print
Learning good representations on multi-relational graphs is essential to knowledge base completion (KBC).  ...  larger embedding sizes are used.  ...  Over the past years, most of the research on KBC has been focusing on Knowledge Graph Embedding models, which learn representations for all entities and relations in a Knowledge Graph, and use them for  ... 
arXiv:2110.02834v1 fatcat:4hknrtkssndihkaatns7vfdv24

Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion [article]

Guanglin Niu, Yang Li, Chengguang Tang, Ruiying Geng, Jian Dai, Qiao Liu, Hao Wang, Jian Sun, Fei Huang, Luo Si
2021 arXiv   pre-print
Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs), few-shot knowledge graph completion (FKGC) has recently gained more research interests.  ...  Moreover, modeling and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and many-to-many (N-N) by previous knowledge graph completion approaches requires high model complexity and a  ...  INTRODUCTION Knowledge graph (KG) stores rich multi-relational data in a directed graph structure.  ... 
arXiv:2104.13095v2 fatcat:yy4bharuvjemjho7zfcteuptia

Hyper-node Relational Graph Attention Network for Multi-modal Knowledge Graph Completion

Shuang Liang, Anjie Zhu, Jiasheng Zhang, Jie Shao
2022 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
However, most existing knowledge graph embedding methods only use the relational information of knowledge graph and treat the entities and relations as IDs with simple embedding layer, ignoring the multi-modal  ...  Knowledge graphs often suffer from incompleteness, and knowledge graph completion (KGC) aims at inferring the missing triplets through knowledge graph embedding from known factual triplets.  ...  [8] take advantage of knowledge graph embedding to improve the performance of image retrieval for complex queries.  ... 
doi:10.1145/3545573 fatcat:i4eviv6q4nd5xi2dkmysvxnqhy

A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization [article]

Dai Quoc Nguyen and Thanh Vu and Tu Dinh Nguyen and Dat Quoc Nguyen and Dinh Phung
2019 arXiv   pre-print
Our proposed CapsE obtains better performance than previous state-of-the-art embedding models for knowledge graph completion on two benchmark datasets WN18RR and FB15k-237, and outperforms strong search  ...  In this paper, we introduce an embedding model, named CapsE, exploring a capsule network to model relationship triples (subject, relation, object).  ...  Knowledge graph completion evaluation In the knowledge graph completion task (Bordes et al., 2013) , the goal is to predict a missing entity given a relation and another entity, i.e, inferring a head  ... 
arXiv:1808.04122v3 fatcat:rytgvekczfbbhl26e7bi6pd6rq

Efficiently Embedding Dynamic Knowledge Graphs [article]

Tianxing Wu, Arijit Khan, Huan Gao, Cheng Li
2019 arXiv   pre-print
., knowledge embedding and contextual element embedding) for each entity and each relation, in the joint modeling of entities and relations as well as their contexts, by employing two attentive graph convolutional  ...  Knowledge graph (KG) embedding encodes the entities and relations from a KG into low-dimensional vector spaces to support various applications such as KG completion, question answering, and recommender  ...  Different from KG embedding, graph embedding usually only learns vertex embeddings based on structural proximities without considering relational semantics on edges.  ... 
arXiv:1910.06708v1 fatcat:ezgc7qdxofaw5fyhyrjeg7wroa

Is There More Pattern in Knowledge Graph? Exploring Proximity Pattern for Knowledge Graph Embedding [article]

Ren Li, Yanan Cao, Qiannan Zhu, Xiaoxue Li, Fang Fang
2021 arXiv   pre-print
Modeling of relation pattern is the core focus of previous Knowledge Graph Embedding works, which represents how one entity is related to another semantically by some explicit relation.  ...  Being evaluated on FB15k-237 and WN18RR datasets, CP-GNN achieves state-of-the-art results for Knowledge Graph Completion task, and can especially boost the modeling capacity for complex queries that contain  ...  During encoding step, the initial entity embedding E is sequently modeled by a relation aware GNN G r on knowledge graph and a homogeneous GNN G p on proximity graph.  ... 
arXiv:2110.00720v1 fatcat:ipkjfjirynelvf2xt7wiejpafe
« Previous Showing results 1 — 15 out of 8,398 results