Temporal Network Embedding for Link Prediction via VAE Joint Attention Mechanism

Jiao, Pengfei; Guo, Xuan; Jing, Xin; He, Dongxiao; Wu, Huaming; Pan, Shirui; Gong, Maoguo; Wang, Wenjun

doi:10.1109/tnnls.2021.3084957

Cited by 39 publications

(17 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In recent years, attention mechanism has been applied to achieve better FER results in the presence of partially occluded faces (Abdullah et al 2019;Maraza et al 2020). The attention mechanism in FER draws on the human visual selective attention mechanism; that is, the human eye quickly scans global images to obtain the target region to be focused on (Jiao et al 2021). Therefore, more attentional resources are invested in this focus region to obtain more detailed features, and useless information is suppressed.…”

Section: Fervr Frameworkmentioning

confidence: 99%

A method for evaluating the learning concentration in head-mounted virtual reality interaction

2022

View full text Add to dashboard Cite

In education, learning concentration is closely related to the quality of learning, and teachers can adjust their teaching methods accordingly to improve the learning outcomes of students. Particularly in head-mounted virtual reality interactions, current methods for assessing learning concentration cannot be fully applied to new interactive environments because immersion shaping and cognitive formation differ from the conventional education. Therefore, in this study, a learning concentration assessment method is proposed to measure the learning concentration of students in head-mounted virtual interaction, using the expression score, visual focus rate, and task mastery as evaluation indicators. In addition, the weights of the evaluation indicators can be configured to be included in the calculation of learning concentration depending on the characteristics of different types of courses. The results of a usability evaluation indicate that the learning concentration of students can be effectively evaluated using the proposed method. By developing and implementing strategies for optimizing learning effects, the learning concentration and assessment scores of students increased by 18% and 15.39%, respectively.

show abstract

Section: Fervr Frameworkmentioning

confidence: 99%

A method for evaluating the learning concentration in head-mounted virtual reality interaction

2022

View full text Add to dashboard Cite

show abstract

“…They utilized the encoder to learn a highly nonlinear network structure, then employed LSTM to learn the temporal dependence of network sequences. Jiao et al [25] considered that the node vectors need to contain evolution information of network topology. Therefore, they introduced graph attention networks (GAT) between encoder and decoder that captured topological information.…”

Section: Deep Learning-based Link Predictionmentioning

confidence: 99%

Link Prediction Model for Opportunistic Networks Based on Feature Fusion

2022

View full text Add to dashboard Cite

Link prediction is a hot issue in the research of network evolution. The existing methods employ a stacked structure, which feeds captured topology information into a time series model. However, the structure introduces network noise that affects the accurate extraction of temporal features and reduces the prediction accuracy. Motivated by feature fusion methods in the Computer Vision(CV), we introduce a link prediction model based on attentional feature fusion (AFF-LP), which automatically extracts network features through the Deep Learning. The proposed model leverages the self-attention mechanism to extract the topological and temporal features respectively. Moreover, the network features are fused based on a graph-level representation. With the help of a vector mapping model, the feature vectors are mapped to the future network topology. Three real opportunistic network datasets, ITC, MIT and Infocom06, are used for experiments. The experimental results show that the proposed model is more accurate and stable compared to other baseline methods.

show abstract

“…Hence, it is necessary to reconstruct the missing information before further processing. Most of the methods developed for this purpose try to perform link prediction [ 49 – 51 ], although a more complicated problem arises when the graph nodes are missing. Therefore, due to the complexity of addressing this problem, which we refer to as graph completion, few methods have been presented to solve it.…”

Section: Related Workmentioning

confidence: 99%

SCGG: A deep structure-conditioned graph generative model

et al. 2022

View full text Add to dashboard Cite

Deep learning-based graph generation approaches have remarkable capacities for graph data modeling, allowing them to solve a wide range of real-world problems. Making these methods able to consider different conditions during the generation procedure even increases their effectiveness by empowering them to generate new graph samples that meet the desired criteria. This paper presents a conditional deep graph generation method called SCGG that considers a particular type of structural conditions. Specifically, our proposed SCGG model takes an initial subgraph and autoregressively generates new nodes and their corresponding edges on top of the given conditioning substructure. The architecture of SCGG consists of a graph representation learning network and an autoregressive generative model, which is trained end-to-end. More precisely, the graph representation learning network is designed to compute continuous representations for each node in a graph, which are not only affected by the features of adjacent nodes, but also by the ones of farther nodes. This network is primarily responsible for providing the generation procedure with the structural condition, while the autoregressive generative model mainly maintains the generation history. Using this model, we can address graph completion, a rampant and inherently difficult problem of recovering missing nodes and their associated edges of partially observed graphs. The computational complexity of the SCGG method is shown to be linear in the number of graph nodes. Experimental results on both synthetic and real-world datasets demonstrate the superiority of our method compared with state-of-the-art baselines.

show abstract

Temporal Network Embedding for Link Prediction via VAE Joint Attention Mechanism

Cited by 39 publications

References 43 publications

A method for evaluating the learning concentration in head-mounted virtual reality interaction

A method for evaluating the learning concentration in head-mounted virtual reality interaction

Link Prediction Model for Opportunistic Networks Based on Feature Fusion

SCGG: A deep structure-conditioned graph generative model

Contact Info

Product

Resources

About