RoSANE: Robust and scalable attributed network embedding for sparse networks

Hou, Chengbin; He, Shan; Tang, Ke

doi:10.1016/j.neucom.2020.05.080

Cited by 16 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attributed networks can better represent real-world networked interactions and information as they introduce the auxiliary information via node or edge attributes [104], [105]. The node attributes describe the features of nodes within interactions or relations, while the edge attributes capture information about how the adjacent nodes interact with others in the networks [104].…”

Section: A How To Represent Networked Datamentioning

confidence: 99%

“…Structural complexity of large-scale networks with thousands and millions of nodes results from a complicated and higher-order inner structure [117], which are common in DTs like city IoT [111] and DT of manufacturing with big data [118]. Structural complexity of sparse networks, given fewer edges, lies in their restrictions of attributes processing [105], [119] and optimal modelling [120]. There is an even more complex case for large sparse networks where both complicated large-scale inner structure and problematic sparse edges are involved [120].…”

Section: A How To Represent Networked Datamentioning

confidence: 99%

See 1 more Smart Citation

Towards Digital Twin Oriented Modelling of Complex Networked Systems and Their Dynamics: A Comprehensive Survey

Wen¹,

Gabrys²,

Musiał³

2022

Preprint

View full text Add to dashboard Cite

This paper aims to provide a comprehensive critical overview on how entities and their interactions in Complex Networked Systems (CNS) are modelled across disciplines as they approach their ultimate goal of creating a Digital Twin (DT) that perfectly matches the reality. We propose a new framework to conceptually compare diverse existing modelling paradigms from different perspectives and create unified assessment criteria to assess their respective capabilities of reaching such an ultimate goal. Using the proposed criteria, we also appraise how far the reviewed current state-of-the-art approaches are from the idealised DTs. We also identify and propose potential directions and ways of building a DT-orientated CNS based on the convergence and integration of CNS and DT utilising a variety of cross-disciplinary techniques.

show abstract

Section: A How To Represent Networked Datamentioning

confidence: 99%

Section: A How To Represent Networked Datamentioning

confidence: 99%

Towards Digital Twin Oriented Modelling of Complex Networked Systems and Their Dynamics: A Comprehensive Survey

Wen¹,

Gabrys²,

Musiał³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…SANE (Liu et al 2019) enforces the alignment of a locally linear relationship between each node and its K-nearest neighbors in topology and attribute space to learn the joint embedding representations. RoSANE (Hou et al 2020) first proposes a generic embedding framework that allows to integrate different sources of information together, then selects some techniques such as random walks to guarantee the scalability.…”

Section: Related Workmentioning

confidence: 99%

Attention based adversarially regularized learning for network embedding

Wang

2021

Data Min Knowl Disc

View full text Add to dashboard Cite

Network embedding, also known as graph embedding and network representation learning, is an effective method for representing graphs or network data in a lowdimensional space. Most existing methods focus on preserving network topology and minimizing the reconstruction errors to learn a low-dimensional embedding vector representation of the network. In addition, some researchers are devoted to the embedding learning of attribute networks. These researchers usually study the two matrices of network structure and network attributes separately, and then merge them to realize the embedding learning representation of attribute networks. These studies have different performances on a variety of downstream tasks. However, most of these methods have two problems: first, these methods mostly use shallow model to learn structure or attribute embedding, which do not make full use of the rich information contained in the network, such as the neighborhood information of nodes; second, the distribution of the learned network low-dimensional vector representation is overlooked, which leads to poor generalization ability of the model in some real-world network data. Therefore, this paper proposes an adversarially regularized network representation learning model based on attention mechanism, which encodes the topology features and content information of the network into a low-dimensional embedding vector representation through a graph attention autoencoder. Meanwhile, through an adversarial training schema, the learned low-dimensional vector representation could circumvent the requirement of an explicit prior distribution, and thus obtain better generaliza-Responsible editor: Michelangelo Ceci.

show abstract

“…In addition to the topological structure of nodes connected by edges, the nodes or edges themselves always carry attribute information-that is, they form an attributed network. The attributes can be used as complementary information to overcome the sparsity of topological structure [10,11]. However, these two sources of information may be contradictory to each other in some cases [12].…”

Section: Introductionmentioning

confidence: 99%

“…Nonnegative matrix factorization can also be used to obtain the representation of nodes. SCI [10] proposes a non-negative matrix factorization model with two sets of parameters. SCD [26] introduces an additional community relationship indicator matrix.…”

Section: Introductionmentioning

confidence: 99%

Overlapping Community Detection Based on Attribute Augmented Graph

Lin

Zhan

Zhao

et al. 2021

Entropy

View full text Add to dashboard Cite

There is a wealth of information in real-world social networks. In addition to the topology information, the vertices or edges of a social network often have attributes, with many of the overlapping vertices belonging to several communities simultaneously. It is challenging to fully utilize the additional attribute information to detect overlapping communities. In this paper, we first propose an overlapping community detection algorithm based on an augmented attribute graph. An improved weight adjustment strategy for attributes is embedded in the algorithm to help detect overlapping communities more accurately. Second, we enhance the algorithm to automatically determine the number of communities by a node-density-based fuzzy k-medoids process. Extensive experiments on both synthetic and real-world datasets demonstrate that the proposed algorithms can effectively detect overlapping communities with fewer parameters compared to the baseline methods.

show abstract

RoSANE: Robust and scalable attributed network embedding for sparse networks

Cited by 16 publications

References 33 publications

Towards Digital Twin Oriented Modelling of Complex Networked Systems and Their Dynamics: A Comprehensive Survey

Towards Digital Twin Oriented Modelling of Complex Networked Systems and Their Dynamics: A Comprehensive Survey

Attention based adversarially regularized learning for network embedding

Overlapping Community Detection Based on Attribute Augmented Graph

Contact Info

Product

Resources

About