BDNE: A Method of Bi-Directional Distance Network Embedding

Zhu, Dongjie; Sun, Yu; Cao, N.; Qiao, Xueming; Xu, Ming; Li, Jinlin; Yang, Junzhou

doi:10.1109/cyberc.2019.00036

Cited by 4 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, these "sentences" are used as the input of the Skip-Gram model [18] to learn the low-dimensional vector representation. Since 2016, many methods are refined versions based on DeepWalk [6], [25]. For example, Node2Vec [6] refines the node sequence generation strategy instead of adopting a completely random walk strategy.…”

Section: Network Embeddingmentioning

confidence: 99%

MHNF: Multi-hop Heterogeneous Neighborhood information Fusion graph representation learning

Sun¹,

Zhu²,

Du³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Attention mechanism enables the Graph Neural Networks(GNNs) to learn the attention weights between the target node and its one-hop neighbors, the performance is further improved. However, the most existing GNNs are oriented to homogeneous graphs and each layer can only aggregate the information of one-hop neighbors. Stacking multi-layer networks will introduce a lot of noise and easily lead to over smoothing. We propose a Multi-hop Heterogeneous Neighborhood information Fusion graph representation learning method (MHNF). Specifically, we first propose a hybrid metapath autonomous extraction model to efficiently extract multi-hop hybrid neighbors. Then, we propose a hop-level heterogeneous Information aggregation model, which selectively aggregates different-hop neighborhood information within the same hybrid metapath. Finally, a hierarchical semantic attention fusion model (HSAF) is proposed, which can efficiently integrate different-hop and different-path neighborhood information respectively. This paper can solve the problem of aggregating the multi-hop neighborhood information and can learn hybrid metapaths for target task, reducing the limitation of manually specifying metapaths. In addition, HSAF can extract the internal node information of the metapaths and better integrate the semantic information of different levels. Experimental results on real datasets show that MHNF is superior to state-of-the-art methods in node classification and clustering tasks (10.94% -69.09% and 11.58% -394.93% relative improvement on average, respectively).

show abstract

Section: Network Embeddingmentioning

confidence: 99%

MHNF: Multi-hop Heterogeneous Neighborhood information Fusion graph representation learning

Sun¹,

Zhu²,

Du³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the area of IoT, data are accumulating in a variety of formats, and traditional methods are no longer suitable for large-scale and diverse data scenarios. In recent years, with the development of deep learning and network representation learning [24], network entity alignment based on network embedding [12], [25] has received increasing attentionfor example, PALE [12]. First, PALE embeds the network into a low-dimensional feature space in which each node is represented as a feature vector that contains rich structural and semantic features.…”

Section: Network Alignmentmentioning

confidence: 99%

HUNA: A Method of Hierarchical Unsupervised Network Alignment for IoT

Zhu

Sun

et al. 2021

IEEE Internet Things J.

Self Cite

View full text Add to dashboard Cite

With the advent of the era of the Internet of Things (IoT), a large number of interconnected smart devices form a huge network. The network can be abstracted as a graph, and we propose to identify similar IoT devices in different networks by graph alignment. However, most methods rely on prelabeled cross-network node pairs such as anchor links, which are difficult to obtain due to personal privacy and security restrictions, especially in IoT. In addition, existing network entity alignment methods focus on individual pairs of nodes but ignore the tightly connected group structure in the network, which is a significant feature of IoT devices. In this paper, we propose a method of Hierarchical Unsupervised Network Alignment (HUNA) to identify similar IoT devices in different networks by a deep learning approach. First, we propose an Unsupervised Network Alignment method based on cycle adversarial networks (UNA), which utilizes the adversarial characteristics of cycle adversarial networks to achieve entity alignment under unsupervised conditions. Second, we further expand the model by carefully designing the group structure aggregation optimization module to aggregate the nodes with closely related attributes and structures into a coarse-grained node and align the coarse-grained nodes. Finally, we evaluate HUNA with real and synthetic datasets. Experimental results show that this method can improve the accuracy of node alignment by 10% and perform well in terms of parameter sensitivity.

show abstract

W-Louvain: A Group Detection Algorithm Based on Synthetic Vectors

Qiao

Zhang

et al. 2021

Advances in Artificial Intelligence and Security

View full text Add to dashboard Cite

BDNE: A Method of Bi-Directional Distance Network Embedding

Cited by 4 publications

References 5 publications

MHNF: Multi-hop Heterogeneous Neighborhood information Fusion graph representation learning

MHNF: Multi-hop Heterogeneous Neighborhood information Fusion graph representation learning

HUNA: A Method of Hierarchical Unsupervised Network Alignment for IoT

W-Louvain: A Group Detection Algorithm Based on Synthetic Vectors

Contact Info

Product

Resources

About