scholarly journals Heterogeneous Attributed Network Embedding with Graph Convolutional Networks

2019 ◽  
Vol 33 ◽  
pp. 10061-10062 ◽  
Author(s):  
Yueyang Wang ◽  
Ziheng Duan ◽  
Binbing Liao ◽  
Fei Wu ◽  
Yueting Zhuang
Keyword(s):  
Real World ◽  
Network Embedding ◽  
High Quality ◽  
Embedding Method ◽  
The Real ◽  
Convolutional Networks ◽  
Attributed Network ◽  
Node Attributes ◽  
Attributed Networks

Network embedding which assigns nodes in networks to lowdimensional representations has received increasing attention in recent years. However, most existing approaches, especially the spectral-based methods, only consider the attributes in homogeneous networks. They are weak for heterogeneous attributed networks that involve different node types as well as rich node attributes and are common in real-world scenarios. In this paper, we propose HANE, a novel network embedding method based on Graph Convolutional Networks, that leverages both the heterogeneity and the node attributes to generate high-quality embeddings. The experiments on the real-world dataset show the effectiveness of our method.

scholarly journals DGE: Deep Generative Network Embedding Based on Commonality and Individuality

2020 ◽  
Vol 34 (04) ◽  
pp. 6949-6956
Author(s):  
Sheng Zhou ◽  
Xin Wang ◽  
Jiajun Bu ◽  
Martin Ester ◽  
Pinggang Yu ◽  
...  
Keyword(s):  
Network Topology ◽  
Real World ◽  
Information Source ◽  
Model Parameters ◽  
Network Embedding ◽  
Generative Process ◽  
Attributed Network ◽  
Node Attributes ◽  
Real World Datasets ◽  
The One

Network embedding plays a crucial role in network analysis to provide effective representations for a variety of learning tasks. Existing attributed network embedding methods mainly focus on preserving the observed node attributes and network topology in the latent embedding space, with the assumption that nodes connected through edges will share similar attributes. However, our empirical analysis of real-world datasets shows that there exist both commonality and individuality between node attributes and network topology. On the one hand, similar nodes are expected to share similar attributes and have edges connecting them (commonality). On the other hand, each information source may maintain individual differences as well (individuality). Simultaneously capturing commonality and individuality is very challenging due to their exclusive nature and existing work fail to do so. In this paper, we propose a deep generative embedding (DGE) framework which simultaneously captures commonality and individuality between network topology and node attributes in a generative process. Stochastic gradient variational Bayesian (SGVB) optimization is employed to infer model parameters as well as the node embeddings. Extensive experiments on four real-world datasets show the superiority of our proposed DGE framework in various tasks including node classification and link prediction.

scholarly journals Outlier Aware Network Embedding for Attributed Networks

2019 ◽  
Vol 33 ◽  
pp. 12-19 ◽  
Author(s):  
Sambaran Bandyopadhyay ◽  
N. Lokesh ◽  
M. N. Murty
Keyword(s):  
Integrated Approach ◽  
Network Embedding ◽  
Network Mining ◽  
Embedding Technique ◽  
Attributed Network ◽  
Machine Learning Applications ◽  
Node Attributes ◽  
Robust Network ◽  
Network Approaches ◽  
Attributed Networks

Attributed network embedding has received much interest from the research community as most of the networks come with some content in each node, which is also known as node attributes. Existing attributed network approaches work well when the network is consistent in structure and attributes, and nodes behave as expected. But real world networks often have anomalous nodes. Typically these outliers, being relatively unexplainable, affect the embeddings of other nodes in the network. Thus all the downstream network mining tasks fail miserably in the presence of such outliers. Hence an integrated approach to detect anomalies and reduce their overall effect on the network embedding is required.Towards this end, we propose an unsupervised outlier aware network embedding algorithm (ONE) for attributed networks, which minimizes the effect of the outlier nodes, and hence generates robust network embeddings. We align and jointly optimize the loss functions coming from structure and attributes of the network. To the best of our knowledge, this is the first generic network embedding approach which incorporates the effect of outliers for an attributed network without any supervision. We experimented on publicly available real networks and manually planted different types of outliers to check the performance of the proposed algorithm. Results demonstrate the superiority of our approach to detect the network outliers compared to the state-of-the-art approaches. We also consider different downstream machine learning applications on networks to show the efficiency of ONE as a generic network embedding technique. The source code is made available at https://github.com/sambaranban/ONE.

Extending Proximity Measures to Attributed Networks for Community Detection

2021 ◽  
Vol 30 (4) ◽  
pp. 441-455
Author(s):  
Rinat Aynulin ◽  
◽  
Pavel Chebotarev ◽  
◽  
Keyword(s):  
Network Analysis ◽  
Community Detection ◽  
Network Structure ◽  
Real World ◽  
Adjacency Matrix ◽  
Attribute Information ◽  
Node Attributes ◽  
Proximity Measures ◽  
Definition Of ◽  
Attributed Networks

Proximity measures on graphs are extensively used for solving various problems in network analysis, including community detection. Previous studies have considered proximity measures mainly for networks without attributes. However, attribute information, node attributes in particular, allows a more in-depth exploration of the network structure. This paper extends the definition of a number of proximity measures to the case of attributed networks. To take node attributes into account, attribute similarity is embedded into the adjacency matrix. Obtained attribute-aware proximity measures are numerically studied in the context of community detection in real-world networks.

Hyperspherical Variational Co-embedding for Attributed Networks

2022 ◽  
Vol 40 (3) ◽  
pp. 1-36
Author(s):  
Jinyuan Fang ◽  
Shangsong Liang ◽  
Zaiqiao Meng ◽  
Maarten De Rijke
Keyword(s):  
Euclidean Space ◽  
Poor Performance ◽  
Building Blocks ◽  
Heterogeneous Data ◽  
User Profiling ◽  
Network Embedding ◽  
Stream Network ◽  
Attributed Network ◽  
Von Mises ◽  
Attributed Networks

Network-based information has been widely explored and exploited in the information retrieval literature. Attributed networks, consisting of nodes, edges as well as attributes describing properties of nodes, are a basic type of network-based data, and are especially useful for many applications. Examples include user profiling in social networks and item recommendation in user-item purchase networks. Learning useful and expressive representations of entities in attributed networks can provide more effective building blocks to down-stream network-based tasks such as link prediction and attribute inference. Practically, input features of attributed networks are normalized as unit directional vectors. However, most network embedding techniques ignore the spherical nature of inputs and focus on learning representations in a Gaussian or Euclidean space, which, we hypothesize, might lead to less effective representations. To obtain more effective representations of attributed networks, we investigate the problem of mapping an attributed network with unit normalized directional features into a non-Gaussian and non-Euclidean space. Specifically, we propose a hyperspherical variational co-embedding for attributed networks (HCAN), which is based on generalized variational auto-encoders for heterogeneous data with multiple types of entities. HCAN jointly learns latent embeddings for both nodes and attributes in a unified hyperspherical space such that the affinities between nodes and attributes can be captured effectively. We argue that this is a crucial feature in many real-world applications of attributed networks. Previous Gaussian network embedding algorithms break the assumption of uninformative prior, which leads to unstable results and poor performance. In contrast, HCAN embeds nodes and attributes as von Mises-Fisher distributions, and allows one to capture the uncertainty of the inferred representations. Experimental results on eight datasets show that HCAN yields better performance in a number of applications compared with nine state-of-the-art baselines.

TrainWorld: A Powerful Tool for Railway Timetabling

2013 ◽  
Author(s):  
I-Chang Chen ◽  
Shu-Keng Hsu ◽  
Hsiu-Hao Hsu ◽  
Chuen-Yih Chen ◽  
Dung-Ying Lin ◽  
...  
Keyword(s):  
Real World ◽  
Software System ◽  
High Quality ◽  
The Real ◽  
Center Stage ◽  
Railway System ◽  
Railway Timetabling ◽  
Complicated Task

Planning for the operation of a railway system is a very complicated task. At the center stage of this planning work is timetabling. In this work we present TrainWorld, a powerful, sophisticated software system that, among other capabilities, is able to solve for high-quality timetables for real-sized, complicated railways. Testing with Taiwan Railways Administration (TRA) data demonstrates the ability of TrainWorld in solving for real-world timetables. The TRA system has 224 stations, approximately three-quarters of the 1085Km railway are double-tracked, and the rest are single-tracked. The system offers close to 1000 daily services in its 18-hour operation hours. Some busy stations carry more than 280 services a day, resulting in an eight-minute average headway between trains. TrainWorld is able to solve a timetable for such a system in approximately 70 hours, and the result is close to the real timetable.

scholarly journals Learning Signed Network Embedding via Graph Attention

2020 ◽  
Vol 34 (04) ◽  
pp. 4772-4779 ◽  
Author(s):  
Yu Li ◽  
Yuan Tian ◽  
Jiawei Zhang ◽  
Yi Chang
Keyword(s):  
Network Analysis ◽  
Real World ◽  
Link Prediction ◽  
Critical Role ◽  
Network Embedding ◽  
Convolutional Networks ◽  
Importance Coefficient ◽  
Signed Network ◽  
Low Dimensional ◽  
Negative Links

Learning the low-dimensional representations of graphs (i.e., network embedding) plays a critical role in network analysis and facilitates many downstream tasks. Recently graph convolutional networks (GCNs) have revolutionized the field of network embedding, and led to state-of-the-art performance in network analysis tasks such as link prediction and node classification. Nevertheless, most of the existing GCN-based network embedding methods are proposed for unsigned networks. However, in the real world, some of the networks are signed, where the links are annotated with different polarities, e.g., positive vs. negative. Since negative links may have different properties from the positive ones and can also significantly affect the quality of network embedding. Thus in this paper, we propose a novel network embedding framework SNEA to learn Signed Network Embedding via graph Attention. In particular, we propose a masked self-attentional layer, which leverages self-attention mechanism to estimate the importance coefficient for pair of nodes connected by different type of links during the embedding aggregation process. Then SNEA utilizes the masked self-attentional layers to aggregate more important information from neighboring nodes to generate the node embeddings based on balance theory. Experimental results demonstrate the effectiveness of the proposed framework through signed link prediction task on several real-world signed network datasets.

scholarly journals Deep attributed network embedding by mutual information maximization

2021 ◽  
Vol 2132 (1) ◽  
pp. 012035
Author(s):  
Wujun Tao ◽  
Yu Ye ◽  
Bailin Feng
Keyword(s):  
Mutual Information ◽  
Network Embedding ◽  
Structure Information ◽  
Attributed Network ◽  
Information Maximization ◽  
Node Attributes ◽  
Real World Datasets ◽  
Low Dimensional ◽  
Mutual Information Maximization ◽  
Node Embeddings

Abstract There is a growing body of literature that recognizes the importance of network embedding. It intends to encode the graph structure information into a low-dimensional vector for each node in the graph, which benefits the downstream tasks. Most of recent works focus on supervised learning. But they are usually not feasible in real-world datasets owing to the high cost to obtain labels. To address this issue, we design a new unsupervised attributed network embedding method, deep attributed network embedding by mutual information maximization (DMIM). Our method focuses on maximizing mutual information between the hidden representations of the global topological structure and the node attributes, which allows us to obtain the node embedding without manual labeling. To illustrate the effectiveness of our method, we carry out the node classification task using the learned node embeddings. Compared with the state-of-the-art unsupervised methods, our method achieves superior results on various datasets.

scholarly journals Deep Attributed Network Embedding

2018 ◽  
Author(s):  
Hongchang Gao ◽  
Heng Huang
Keyword(s):  
Topological Structure ◽  
Link Prediction ◽  
Network Embedding ◽  
Dimensional Representation ◽  
Attributed Network ◽  
Real World Applications ◽  
Benchmark Datasets ◽  
Node Attributes ◽  
Novel Strategy ◽  
Low Dimensional

Network embedding has attracted a surge of attention in recent years. It is to learn the low-dimensional representation for nodes in a network, which benefits downstream tasks such as node classification and link prediction. Most of the existing approaches learn node representations only based on the topological structure, yet nodes are often associated with rich attributes in many real-world applications. Thus, it is important and necessary to learn node representations based on both the topological structure and node attributes. In this paper, we propose a novel deep attributed network embedding approach, which can capture the high non-linearity and preserve various proximities in both topological structure and node attributes. At the same time, a novel strategy is proposed to guarantee the learned node representation can encode the consistent and complementary information from the topological structure and node attributes. Extensive experiments on benchmark datasets have verified the effectiveness of our proposed approach.

scholarly journals Multiplex Network Embedding Model with High-Order Node Dependence

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Nianwen Ning ◽  
Qiuyue Li ◽  
Kai Zhao ◽  
Bin Wu
Keyword(s):  
Real World ◽  
Information Diffusion ◽  
Structural Information ◽  
High Order ◽  
Network Embedding ◽  
Multiplex Networks ◽  
Cross Domain ◽  
Multiplex Network ◽  
Node Attributes ◽  
Two Phases

Multiplex networks have been widely used in information diffusion, social networks, transport, and biology multiomics. They contain multiple types of relations between nodes, in which each type of the relation is intuitively modeled as one layer. In the real world, the formation of a type of relations may only depend on some attribute elements of nodes. 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. To address this problem, we propose a novel multiplex network embedding model with high-order node dependence, called HMNE. HMNE simultaneously considers three properties: (1) intralayer high-order proximity of nodes, (2) interlayer dependence in respect of nodes, and (3) the dependence between node attributes and the topology of each layer. In the intralayer embedding phase, we present a symmetric graph convolution-deconvolution model to embed high-order proximity information as the intralayer embedding of nodes in an unsupervised manner. In the interlayer embedding phase, we estimate the local structural complementarity of nodes as an embedding constraint of interlayer dependence. Through these two phases, we can achieve the disentangled representation of node attributes, which can be treated as fined-grained semantic dependence on the topology of each layer. In the restructure phase of node attributes, we perform a linear fusion of attribute disentangled representations for each node as a reconstruction of original attributes. Extensive experiments have been conducted on six real-world networks. The experimental results demonstrate that the proposed model outperforms the state-of-the-art methods in cross-domain link prediction and shared community detection tasks.

Sign in / Sign up

Export Citation Format

Share Document