RAGAT: Relation Aware Graph Attention Network for Knowledge Graph Completion

Liu, Xiyang; Tan, Huobin; Chen, Qinghong; Lin, Guanghui

doi:10.1109/access.2021.3055529

Cited by 46 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GraphSAGE minimizes information loss by concatenating vectors of neighbors rather than summing them into a single value in the process of neighbor aggregation [40,41]. GAT utilizes the concept of attention to individually deal with the importance of neighbor nodes or relations [21,[42][43][44][45][46][47]. Since each model has different characteristics and advantages, suitable models for KG alignment differ depending on the components and the topological structure of the KG.…”

Section: Knowledge Graph Alignmentmentioning

confidence: 99%

Graph Representation Learning-Based Early Depression Detection Framework in Smart Home Environments

Kim

Sohn

2022

Sensors

View full text Add to dashboard Cite

Although the diagnosis and treatment of depression is a medical field, ICTs and AI technologies are used widely to detect depression earlier in the elderly. These technologies are used to identify behavioral changes in the physical world or sentiment changes in cyberspace, known as symptoms of depression. However, although sentiment and physical changes, which are signs of depression in the elderly, are usually revealed simultaneously, there is no research on them at the same time. To solve the problem, this paper proposes knowledge graph-based cyber–physical view (CPV)-based activity pattern recognition for the early detection of depression, also known as KARE. In the KARE framework, the knowledge graph (KG) plays key roles in providing cross-domain knowledge as well as resolving issues of grammatical and semantic heterogeneity required in order to integrate cyberspace and the physical world. In addition, it can flexibly express the patterns of different activities for each elderly. To achieve this, the KARE framework implements a set of new machine learning techniques. The first is 1D-CNN for attribute representation in relation to learning to connect the attributes of physical and cyber worlds and the KG. The second is the entity alignment with embedding vectors extracted by the CNN and GNN. The third is a graph extraction method to construct the CPV from KG with the graph representation learning and wrapper-based feature selection in the unsupervised manner. The last one is a method of activity-pattern graph representation based on a Gaussian Mixture Model and KL divergence for training the GAT model to detect depression early. To demonstrate the superiority of the KARE framework, we performed the experiments using real-world datasets with five state-of-the-art models in knowledge graph entity alignment.

show abstract

Section: Knowledge Graph Alignmentmentioning

confidence: 99%

Graph Representation Learning-Based Early Depression Detection Framework in Smart Home Environments

Kim

Sohn

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…However, using multi-head attention can have large size of parameters. To address this issue, relation aware graph attention network (RAGAT) [47] is proposed which de nes relation aware message passing functions parameterized by relation speci c network parameters and employs averaging instead of concatenating n attention head. To validate the results of this model, the decoder (scoring function) uses two different decoders: ConvE and InteractE.…”

Section: Attention Neural Network Modelsmentioning

confidence: 99%

A review of Knowledge graph link prediction using graph neural networks

Zamini

Reza

Rabiei

2022

Preprint

View full text Add to dashboard Cite

Information extraction methods proved to be effective at triple extraction from structured or unstructured data. The organization of such triples in the form of (head entity, relation, tail entity) is called the construction of Knowledge Graphs (KGs). In order to use KGs in downstream tasks it is desirable to predict missing links in KGs. In this review we will study the current approaches and the challenges exists..

show abstract

“…Graph neural networks (GNNs) learn a lower-dimensional representation for a node in a vector space by aggregating the information from its neighbors using discrete hidden layers. Then the embedding can be used for downstream tasks such as node classification (Atwood and Towsley, 2015), link prediction (Zhang and Chen, 2018;Li et al, 2020), and knowledge completion (Liu et al, 2021b).…”

Section: Introductionmentioning

confidence: 99%

Continuous Temporal Graph Networks for Event-Based Graph Data

Guo¹,

Han²,

Zhou³

et al. 2022

Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022)

View full text Add to dashboard Cite

There has been an increasing interest in modeling continuous-time dynamics of temporal graph data. Previous methods encode timeevolving relational information into a lowdimensional representation by specifying discrete layers of neural networks, while realworld dynamic graphs often vary continuously over time. Hence, we propose Continuous Temporal Graph Networks (CTGNs) to capture continuous dynamics of temporal graph data. We use both the link starting timestamps and link duration as evolving information to model continuous dynamics of nodes. The key idea is to use neural ordinary differential equations (ODE) to characterize the continuous dynamics of node representations over dynamic graphs. We parameterize ordinary differential equations using a novel graph neural network. The existing dynamic graph networks can be considered as a specific discretization of CTGNs. Experiment results on both transductive and inductive tasks demonstrate the effectiveness of our proposed approach over competitive baselines.

show abstract

RAGAT: Relation Aware Graph Attention Network for Knowledge Graph Completion

Cited by 46 publications

References 27 publications

Graph Representation Learning-Based Early Depression Detection Framework in Smart Home Environments

Graph Representation Learning-Based Early Depression Detection Framework in Smart Home Environments

A review of Knowledge graph link prediction using graph neural networks

Continuous Temporal Graph Networks for Event-Based Graph Data

Contact Info

Product

Resources

About