A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
Network Data Mining Algorithm of Associated Users Based on Multi-Information Fusion
2022
Security and Communication Networks
To explore how related users can optimize the network mining algorithm, the author proposes a related user mining algorithm based on the fusion of user attributes and user relationships. ...
Also, since the node embedding of the AUMA-MRL algorithm is obtained by neighborhood sampling, for new nodes in the network, the algorithm can quickly obtain the new node embedding, as well as the similarity ...
equation: z v � h k u , v ∈ V. ( 3 ) To obtain an embedding that effectively fuses user attributes and user relationships, so that nodes with similar attributes and structures have similar embedding representations ...
doi:10.1155/2022/9656986
fatcat:teksc2m665cyflcozkfqd33c4y
A Bayesian graph embedding model for link-based classification problems
2021
IEEE Transactions on Network Science and Engineering
This paper introduces a Bayesian graph embedding model for such problems, integrating network reconstruction, link prediction, and behavior prediction into a unified framework. ...
Unlike the existing graph embedding methods, this model does not embed the topology of nodes or links into a low-dimensional space but sorts the probabilities of upcoming links and fuses the information ...
Science Foundation of Shanghai under Grant 17ZR1446000 and Grant 21ZR1422000, in part by the China Postdoctoral Science Foundation under Grant 2020M670998, and in part by the Hong Kong Research Grants ...
doi:10.1109/tnse.2021.3131223
fatcat:bca3p4b5jjci5hc4gh7yqfqrt4
Multi-granularity Complex Network Representation Learning
[chapter]
2020
Lecture Notes in Computer Science
Therefore, it is essential to learn the representation of node based on both the topological structure and node additional attributes. ...
fused information learning into the same granularity semantic space that through fine-to-coarse to refine the complex network. ...
The suspect P4 and P7 are related by the attribute A4, the topology without attribute cannot recognize why the relation between them is generated. ...
doi:10.1007/978-3-030-52705-1_18
fatcat:dfqv2di4r5bxxdnla5mpacp32u
RAGFormer: Learning Semantic Attributes and Topological Structure for Fraud Detection
[article]
2024
arXiv
pre-print
We introduce Relation-Aware GNN as the topology encoder to learn topological features and node interactions within each relation. ...
The simple yet effective network consists of a semantic encoder, a topology encoder, and an attention fusion module. ...
GTAN [32] exploited an attribute-driven gated temporal attention network for credit card fraud detection. ...
arXiv:2402.17472v3
fatcat:z4mohusstvf6pbtplwrlkhte5e
The Deep Fusion of Topological Structure and Attribute Information for Link Prediction
2020
IEEE Access
We get the embedded vectors with topological structure and attribute information by structure encoder and attribute encoder respectively, and fuse two vectors deeply. ...
In this paper, a novel algorithm called Network Embedding with Attribute Deep Fusion for Link Prediction (NEADF-LP) is proposed. ...
In this paper, we propose a novel link prediction method which considers both the topological structure and the attribute information of nodes, namely Network Embedding with Attribute Deep Fusion for Link ...
doi:10.1109/access.2020.2974016
fatcat:fwstuku76nesvafvl3yr7uujgi
Structure-Preserving Graph Representation Learning
[article]
2022
arXiv
pre-print
Most existing methods focus on local structure and fail to fully incorporate the global topological structure. ...
Besides, we retain the global topological structure information by maximizing the mutual information (MI) of the whole graph and feature embeddings, which is theoretically reduced to exchanging the feature ...
Global Graph-level Relation Node contrastive method is not an effective way to attain global structural information in the topology graph. ...
arXiv:2209.00793v2
fatcat:6o3cp55qvvbqjjrsceu4xgnsha
A Deep Graph Network with Multiple Similarity for User Clustering in Human–Computer Interaction
2022
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
This paper focuses on improving the clustering performance of users' attributes in HCI and proposes a deep graph embedding network with feature and structure similarity (called DGENFS) to cluster users ...
Then, the FGA and SGAT modules are utilized to extract the representations of human features and topological space, respectively. ...
This observation indicates the necessity of fusing attribute features and topology for graph clustering. ...
doi:10.1145/3549954
fatcat:v4row2wpufgodkjfvyrflfr2e4
SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks
[article]
2019
arXiv
pre-print
In this paper, we propose a spectral convolution and deconvolution based framework -- SpecAE, to project the attributed network into a tailored space to detect global and community anomalies. ...
However, it remains a challenging task since the definition of anomaly becomes more complicated and topological structures are heterogeneous with nodal attributes. ...
Tailored Embedding Spaces for Global Anomalies and Community Anomalies Attributed networks bring both opportunities and challenges to the anomaly detection task. ...
arXiv:1908.03849v3
fatcat:qdhuhlfyffdnjiaxlrx2izpocy
Multiplex Network Embedding Model with High-Order Node Dependence
2021
Complexity
Most existing multiplex network embedding methods only focus on intralayer and interlayer structural information while neglecting this dependence between node attributes and the topology of each layer. ...
Attributes that are irrelevant to the network structure could affect the embedding quality of multiplex networks. ...
For MELL, we add layer-level embedding as the global-level embedding and then add it to the node-level embedding of the test node. ...
doi:10.1155/2021/6644111
fatcat:qsxs4kyoqrgv5ne2xpuns4qsru
A Semantic-Enhancement-Based Social Network User-Alignment Algorithm
2023
Entropy
The algorithm performs user alignment based on user attributes, user-generated contents (UGCs), and user check-ins. ...
Therefore, we optimize the embedding vectors based on multi-headed graph attention networks and multi-view contrastive learning. This can enhance the similar semantic features of the aligned users. ...
Graph neural networks are commonly used at present to fuse user features and network topologies simultaneously. ...
doi:10.3390/e25010172
pmid:36673313
pmcid:PMC9858570
fatcat:ijgbb4yswrc2vnvyh2ksvg6et4
Subgraph Networks Based Contrastive Learning
[article]
2024
arXiv
pre-print
This strategy converts the original graph into an Edge-to-Node mapping network with both topological and attribute features. ...
In addition, we also investigate the impact of the second-order subgraph augmentation on mining graph structure interactions, and further, propose a contrastive objective that fuses the first-order and ...
This will meet the requirement of the message-passing network [50] for analyzing node attributes, edge attributes, and adjacency relations. ...
arXiv:2306.03506v2
fatcat:wyy3as3qhrbj3kzlxjivk4tvtu
Deep Embedded Clustering with Distribution Consistency Preservation for Attributed Networks
[article]
2022
arXiv
pre-print
Under the assumption of consistency for data in different views, the cluster structure of network topology and that of node attributes should be consistent for an attributed network. ...
Therefore, in this study, we propose an end-to-end deep embedded clustering model for attributed networks. ...
Acknowledgment This work was supported by the National Key R&D Program of China (grant numbers 2017YFC1703506, 2018AAA0100302); and National Natural Science Foundation of China (grant numbers 61876016, ...
arXiv:2205.14303v1
fatcat:q3uu6gndrzfk3lwqqrkq7uq5gu
MFDA: Multiview fusion based on dual-level attention for drug interaction prediction
2022
Frontiers in Pharmacology
The MFDA first constructed multiple views for the drug interaction relationship, and then adopted a cross-fusion strategy to deeply fuse drug features with the drug interaction network under each view. ...
To distinguish the importance of different neighbors and views, MFDA adopted a dual-level attention mechanism (node level and view level) to obtain the unified drug embedding for drug interaction prediction ...
Acknowledgments We acknowledge reviewers for the valuable comments on the original manuscript. ...
doi:10.3389/fphar.2022.1021329
pmid:36278200
pmcid:PMC9584567
fatcat:7oo5tx3ktbcypkivapnjnx3dye
Network Alignment with Holistic Embeddings
2021
IEEE Transactions on Knowledge and Data Engineering
Network alignment is the task of identifying topologically and semantically similar nodes across (two) different networks. ...
In order to exploit the richness of the network context, our model constructs multiple embeddings for each node, each of which captures one modality or type of network information. ...
More specifically, network nodes are embedded * Corresponding author into a low-dimensional space such that the topological and attributional relations between any two nodes in the original network are ...
doi:10.1109/tkde.2021.3101840
fatcat:ougfnzoi4ngmdh2genh6mul4mm
Traffic Intersection Re-Identification Using Monocular Camera Sensors
2020
Sensors
attributes, and global localization in topological maps. ...
Experimental results demonstrate that our proposed approach can achieve promising results in re-ID of both coarse road intersections and its global pose, and is well suited for updating and completion ...
We impose supervision on the coarse features to produce two embedding heads [32] for the classification of intersection and its attributes. ...
doi:10.3390/s20226515
pmid:33202653
pmcid:PMC7696742
fatcat:yguvc7oodnhhlmd3rj5koriefu
« Previous
Showing results 1 — 15 out of 7,603 results