scholarly journals Network Embedding via a Bi-Mode and Deep Neural Network Model

2017 ◽  
Author(s):  
Yang Fang ◽  
Xiang Zhao ◽  
Zhen Tan
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Semantic Information ◽  
Dimensional Space ◽  
Relation Extraction ◽  
Network Embedding ◽  
Structure Information ◽  
Second Mode ◽  
Real World Datasets ◽  
Low Dimensional

Network Embedding (NE) is an important method to learn the representations of network via a low-dimensional space. Conventional NE models focus on capturing the structure information and semantic information of vertices while neglecting such information for edges. In this work, we propose a novel NE model named BimoNet to capture both the structure and semantic information of edges. BimoNet is composed of two parts, i.e., the bi-mode embedding part and the deep neural network part. For bi-mode embedding part, the first mode named add-mode is used to express the entity-shared features of edges and the second mode named subtract-mode is employed to represent the entity-specific features of edges. These features actually reflect the semantic information. For deep neural network part, we firstly regard the edges in a network as nodes, and the vertices as links, which will not change the overall structure of the whole network. Then we take the nodes' adjacent matrix as the input of the deep neural network as it can obtain similar representations for nodes with similar structure. Afterwards, by jointly optimizing the objective function of these two parts, BimoNet could preserve both the semantic and structure information of edges. In experiments, we evaluate BimoNet on three real-world datasets and task of relation extraction, and BimoNet is demonstrated to outperform state-of-the-art baseline models consistently and significantly.

scholarly journals Relation Structure-Aware Heterogeneous Information Network Embedding

2019 ◽  
Vol 33 ◽  
pp. 4456-4463 ◽  
Author(s):  
Yuanfu Lu ◽  
Chuan Shi ◽  
Linmei Hu ◽  
Zhiyuan Liu
Keyword(s):  
Real World ◽  
Dimensional Space ◽  
Structural Characteristics ◽  
Information Network ◽  
Network Embedding ◽  
Heterogeneous Information Network ◽  
Heterogeneous Information ◽  
Real World Datasets ◽  
Low Dimensional ◽  
Embedding Methods

Heterogeneous information network (HIN) embedding aims to embed multiple types of nodes into a low-dimensional space. Although most existing HIN embedding methods consider heterogeneous relations in HINs, they usually employ one single model for all relations without distinction, which inevitably restricts the capability of network embedding. In this paper, we take the structural characteristics of heterogeneous relations into consideration and propose a novel Relation structure-aware Heterogeneous Information Network Embedding model (RHINE). By exploring the real-world networks with thorough mathematical analysis, we present two structure-related measures which can consistently distinguish heterogeneous relations into two categories: Affiliation Relations (ARs) and Interaction Relations (IRs). To respect the distinctive characteristics of relations, in our RHINE, we propose different models specifically tailored to handle ARs and IRs, which can better capture the structures and semantics of the networks. At last, we combine and optimize these models in a unified and elegant manner. Extensive experiments on three real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods in various tasks, including node clustering, link prediction, and node classification.

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.

Community detection in complex network by network embedding and density clustering

2021 ◽  
pp. 1-12
Author(s):  
JinFang Sheng ◽  
Huaiyu Zuo ◽  
Bin Wang ◽  
Qiong Li
Keyword(s):  
Complex Network ◽  
Community Detection ◽  
Dimensional Space ◽  
Detection Algorithm ◽  
Superior Performance ◽  
Network Embedding ◽  
Detection Algorithms ◽  
Density Clustering ◽  
Community Detection Algorithm ◽  
Low Dimensional

 In a complex network system, the structure of the network is an extremely important element for the analysis of the system, and the study of community detection algorithms is key to exploring the structure of the complex network. Traditional community detection algorithms would represent the network using an adjacency matrix based on observations, which may contain redundant information or noise that interferes with the detection results. In this paper, we propose a community detection algorithm based on density clustering. In order to improve the performance of density clustering, we consider an algorithmic framework for learning the continuous representation of network nodes in a low-dimensional space. The network structure is effectively preserved through network embedding, and density clustering is applied in the embedded low-dimensional space to compute the similarity of nodes in the network, which in turn reveals the implied structure in a given network. Experiments show that the algorithm has superior performance compared to other advanced community detection algorithms for real-world networks in multiple domains as well as synthetic networks, especially when the network data chaos is high.

IMPROVEMENT OF IMAGE CLASSIFICATION USING WAVELET COEFFICIENTS WITH STRUCTURED-BASED NEURAL NETWORK

2008 ◽  
Vol 18 (03) ◽  
pp. 195-205 ◽  
Author(s):  
WEIBAO ZOU ◽  
ZHERU CHI ◽  
KING CHUEN LO
Keyword(s):  
Neural Network ◽  
Wavelet Analysis ◽  
Image Classification ◽  
Dimensional Space ◽  
Training Data ◽  
Wavelet Coefficients ◽  
Classification Rate ◽  
Data Set ◽  
Low Dimensional ◽  
High Level

Image classification is a challenging problem in organizing a large image database. However, an effective method for such an objective is still under investigation. A method based on wavelet analysis to extract features for image classification is presented in this paper. After an image is decomposed by wavelet, the statistics of its features can be obtained by the distribution of histograms of wavelet coefficients, which are respectively projected onto two orthogonal axes, i.e., x and y directions. Therefore, the nodes of tree representation of images can be represented by the distribution. The high level features are described in low dimensional space including 16 attributes so that the computational complexity is significantly decreased. 2800 images derived from seven categories are used in experiments. Half of the images were used for training neural network and the other images used for testing. The features extracted by wavelet analysis and the conventional features are used in the experiments to prove the efficacy of the proposed method. The classification rate on the training data set with wavelet analysis is up to 91%, and the classification rate on the testing data set reaches 89%. Experimental results show that our proposed approach for image classification is more effective.

scholarly journals Entity Type Enhanced Neural Model for Distantly Supervised Relation Extraction (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13751-13752
Author(s):  
Long Bai ◽  
Xiaolong Jin ◽  
Chuanzhi Zhuang ◽  
Xueqi Cheng
Keyword(s):  
Neural Network ◽  
Semantic Information ◽  
Relation Extraction ◽  
Neural Model ◽  
Benchmark Dataset ◽  
Experimental Comparison ◽  
Type Information

Distantly Supervised Relation Extraction (DSRE) has been widely studied, since it can automatically extract relations from very large corpora. However, existing DSRE methods only use little semantic information about entities, such as the information of entity type. Thus, in this paper, we propose a method for integrating entity type information into a neural network based DSRE model. It also adopts two attention mechanisms, namely, sentence attention and type attention. The former selects the representative sentences for a sentence bag, while the latter selects appropriate type information for entities. Experimental comparison with existing methods on a benchmark dataset demonstrates its merits.

scholarly journals Unsupervised Deep Video Hashing with Balanced Rotation

2017 ◽  
Author(s):  
Gengshen Wu ◽  
Li Liu ◽  
Yuchen Guo ◽  
Guiguang Ding ◽  
Jungong Han ◽  
...  
Keyword(s):  
State Of The Art ◽  
Dimensional Space ◽  
Image Hashing ◽  
Neighborhood Structure ◽  
Function Learning ◽  
Video Hashing ◽  
Real World Datasets ◽  
Low Dimensional ◽  
Balanced Code ◽  
Hash Codes

Recently, hashing video contents for fast retrieval has received increasing attention due to the enormous growth of online videos. As the extension of image hashing techniques, traditional video hashing methods mainly focus on seeking the appropriate video features but pay little attention to how the video-specific features can be leveraged to achieve optimal binarization. In this paper, an end-to-end hashing framework, namely Unsupervised Deep Video Hashing (UDVH), is proposed, where feature extraction, balanced code learning and hash function learning are integrated and optimized in a self-taught manner. Particularly, distinguished from previous work, our framework enjoys two novelties: 1) an unsupervised hashing method that integrates the feature clustering and feature binarization, enabling the neighborhood structure to be preserved in the binary space; 2) a smart rotation applied to the video-specific features that are widely spread in the low-dimensional space such that the variance of dimensions can be balanced, thus generating more effective hash codes. Extensive experiments have been performed on two real-world datasets and the results demonstrate its superiority, compared to the state-of-the-art video hashing methods. To bootstrap further developments, the source code will be made publically available.

scholarly journals Identifying Disease Related Genes by Network Representation and Convolutional Neural Network

2021 ◽  
Vol 9 ◽  
Author(s):  
Bolin Chen ◽  
Yourui Han ◽  
Xuequn Shang ◽  
Shenggui Zhang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Biological Networks ◽  
Dimensional Space ◽  
Scale Free ◽  
Network Representation ◽  
Disease Related Genes ◽  
Representation Method ◽  
Low Dimensional

The identification of disease related genes plays essential roles in bioinformatics. To achieve this, many powerful machine learning methods have been proposed from various computational aspects, such as biological network analysis, classification, regression, deep learning, etc. Among them, deep learning based methods have gained big success in identifying disease related genes in terms of higher accuracy and efficiency. However, these methods rarely handle the following two issues very well, which are (1) the multifunctions of many genes; and (2) the scale-free property of biological networks. To overcome these, we propose a novel network representation method to transfer individual vertices together with their surrounding topological structures into image-like datasets. It takes each node-induced sub-network as a represented candidate, and adds its environmental characteristics to generate a low-dimensional space as its representation. This image-like datasets can be applied directly in a Convolutional Neural Network-based method for identifying cancer-related genes. The numerical experiments show that the proposed method can achieve the AUC value at 0.9256 in a single network and at 0.9452 in multiple networks, which outperforms many existing methods.

scholarly journals Exploring Chemical Reaction Space With Reaction Difference Fingerprints and Parametric t-SNE

2021 ◽  
Author(s):  
Mikhail Andronov ◽  
Maxim Fedorov ◽  
Sergey Sosnin
Keyword(s):  
Neural Network ◽  
Chemical Reaction ◽  
Deep Neural Network ◽  
Visual Representations ◽  
Dimensional Manifold ◽  
Reaction Space ◽  
Large Databases ◽  
Global Reaction ◽  
Low Dimensional ◽  
Low Dimensional Manifold

<div>Humans prefer visual representations for the analysis of large databases. In this work, we suggest a method for the visualization of the chemical reaction space. Our technique uses the t-SNE approach that is parameterized by a deep neural network (parametric t-SNE). We demonstrated that the parametric t-SNE combined with reaction difference fingerprints can provide a tool for the projection of chemical reactions onto a low-dimensional manifold for easy exploration of reaction space. We showed that the global reaction landscape, been projected onto a 2D plane, corresponds well with already known reaction types. The application of a pretrained parametric t-SNE model to new reactions allows chemists to study these reactions on a global reaction space. We validated the feasibility of this approach for two marketed drugs: darunavir and oseltamivir. We believe that our method can help explore reaction space and inspire chemists to find new reactions and synthetic ways. </div><div><br></div>

Sign in / Sign up

Export Citation Format

Share Document