scholarly journals A Study on Hybrid Hierarchical Network Representation Learning

2021 ◽  
Author(s):  
Yongxiang Hu
Keyword(s):  
Euclidean Space ◽  
Learning Process ◽  
Hybrid Approach ◽  
Representation Learning ◽  
Vector Representation ◽  
Hierarchical Network ◽  
Structure Information ◽  
Low Level ◽  
Network Representation ◽  
High Level

Network representation learning (NRL) aims to convert nodes of a network into vector forms in Euclidean space. The information of a network is needed to be preserved as much as possible when NRL converts nodes into vector representation. A hybrid approach proposed in this paper is a framework to improve other NRL methods by considering the structure of densely connected nodes (community-like structure). HARP [1] is to contract a network into a series of contracted networks and embed them from the high-level contracted network to the low-level one. The vector representation (or embedding) for a high-level contracted network is used to initialize the learning process of a low-level contracted graph hierarchically. In this method (Hybrid Approach), HARP is revised by using a well-designed initialization process on the most high-level contracted network to preserve more community-like structure information.

scholarly journals TransPath: Representation Learning for Heterogeneous Information Networks via Translation Mechanism

2018 ◽  
Author(s):  
Yang Fang ◽  
Xiang Zhao ◽  
Zhen Tan
Keyword(s):  
Large Scale ◽  
Representation Learning ◽  
Information Networks ◽  
Heterogeneous Information ◽  
Structure Information ◽  
Heterogeneous Information Networks ◽  
Network Representation ◽  
Meta Path ◽  
Translation Mechanism ◽  
Real World Datasets

In this paper, we propose a novel network representation learning model TransPath to encode heterogeneous information networks (HINs). Traditional network representation learning models aim to learn the embeddings of a homogeneous network. TransPath is able to capture the rich semantic and structure information of a HIN via meta-paths. We take advantage of the concept of translation mechanism in knowledge graph which regards a meta-path, instead of an edge, as a translating operation from the first node to the last node. Moreover, we propose a user-guided meta-path sampling strategy which takes users' preference as a guidance, which could explore the semantics of a path more precisely, and meanwhile improve model efficiency via the avoidance of other noisy and meaningless meta-paths. We evaluate our model on two large-scale real-world datasets DBLP and YELP, and two benchmark tasks similarity search and node classification. We observe that TransPath outperforms other state-of-the-art baselines consistently and significantly.

scholarly journals TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning

2021 ◽  
Author(s):  
Zhihao Fan ◽  
Zhongyu Wei ◽  
Siyuan Wang ◽  
Ruize Wang ◽  
Zejun Li ◽  
...  
Keyword(s):  
State Of The Art ◽  
Representation Learning ◽  
Experimental Results ◽  
Text Representation ◽  
Image Captioning ◽  
Scene Graph ◽  
Low Level ◽  
Language And Vision ◽  
High Level ◽  
Cross Language

Existing research for image captioning usually represents an image using a scene graph with low-level facts (objects and relations) and fails to capture the high-level semantics. In this paper, we propose a Theme Concepts extended Image Captioning (TCIC) framework that incorporates theme concepts to represent high-level cross-modality semantics. In practice, we model theme concepts as memory vectors and propose Transformer with Theme Nodes (TTN) to incorporate those vectors for image captioning. Considering that theme concepts can be learned from both images and captions, we propose two settings for their representations learning based on TTN. On the vision side, TTN is configured to take both scene graph based features and theme concepts as input for visual representation learning. On the language side, TTN is configured to take both captions and theme concepts as input for text representation re-construction. Both settings aim to generate target captions with the same transformer-based decoder. During the training, we further align representations of theme concepts learned from images and corresponding captions to enforce the cross-modality learning. Experimental results on MS COCO show the effectiveness of our approach compared to some state-of-the-art models.

scholarly journals A Hybrid Approach to Service Recommendation Based on Network Representation Learning

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 60242-60254
Author(s):  
Hao Wu ◽  
Hanyu Zhang ◽  
Peng He ◽  
Cheng Zeng ◽  
Yan Zhang
Keyword(s):  
Hybrid Approach ◽  
Representation Learning ◽  
Service Recommendation ◽  
Network Representation

scholarly journals Network representation learning method embedding linear and nonlinear network structures

Semantic Web ◽  
2022 ◽  
pp. 1-16
Author(s):  
Hu Zhang ◽  
Jingjing Zhou ◽  
Ru Li ◽  
Yue Fan
Keyword(s):  
Rapid Development ◽  
Linear Structure ◽  
Representation Learning ◽  
Nonlinear Structure ◽  
Structure Information ◽  
Nonlinear Network ◽  
Network Representation ◽  
Proposed Model ◽  
Representation Method ◽  
Low Dimensional

With the rapid development of neural networks, much attention has been focused on network embedding for complex network data, which aims to learn low-dimensional embedding of nodes in the network and how to effectively apply learned network representations to various graph-based analytical tasks. Two typical models exist namely the shallow random walk network representation method and deep learning models such as graph convolution networks (GCNs). The former one can be used to capture the linear structure of the network using depth-first search (DFS) and width-first search (BFS), whereas Hierarchical GCN (HGCN) is an unsupervised graph embedding that can be used to describe the global nonlinear structure of the network via aggregating node information. However, the two existing kinds of models cannot simultaneously capture the nonlinear and linear structure information of nodes. Thus, the nodal characteristics of nonlinear and linear structures are explored in this paper, and an unsupervised representation method based on HGCN that joins learning of shallow and deep models is proposed. Experiments on node classification and dimension reduction visualization are carried out on citation, language, and traffic networks. The results show that, compared with the existing shallow network representation model and deep network model, the proposed model achieves better performances in terms of micro-F1, macro-F1 and accuracy scores.

scholarly journals TAXOGAN: Hierarchical Network Representation Learning via Taxonomy Guided Generative Adversarial Networks (Extended Abstract)

2021 ◽  
Author(s):  
Carl Yang ◽  
Jieyu Zhang ◽  
Jiawei Han
Keyword(s):  
Case Studies ◽  
Hierarchical Structures ◽  
Representation Learning ◽  
Generative Adversarial Networks ◽  
Network Embedding ◽  
Hierarchical Network ◽  
Network Representation ◽  
Adversarial Networks ◽  
Node Labels ◽  
The Given

Network representation learning aims at transferring node proximity in networks into distributed vectors, which can be leveraged in various downstream applications. Recent research has shown that nodes in a network can often be organized in latent hierarchical structures, but without a particular underlying taxonomy, the learned node embedding is less useful nor interpretable. In this work, we aim to improve network embedding by modeling the conditional node proximity in networks indicated by node labels residing in real taxonomies. In the meantime, we also aim to model the hierarchical label proximity in the given taxonomies, which is too coarse by solely looking at the hierarchical topologies. Comprehensive experiments and case studies demonstrate the utility of TAXOGAN.

scholarly journals Link Prediction Based on Deep Convolutional Neural Network

Information ◽  
2019 ◽  
Vol 10 (5) ◽  
pp. 172
Author(s):  
Wentao Wang ◽  
Lintao Wu ◽  
Ye Huang ◽  
Hao Wang ◽  
Rongbo Zhu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Link Prediction ◽  
Prediction Method ◽  
Representation Learning ◽  
Deep Convolutional Neural Network ◽  
Published Data ◽  
Neighborhood Structure ◽  
Structure Information ◽  
Network Representation

In recent years, endless link prediction algorithms based on network representation learning have emerged. Network representation learning mainly constructs feature vectors by capturing the neighborhood structure information of network nodes for link prediction. However, this type of algorithm only focuses on learning topology information from the simple neighbor network node. For example, DeepWalk takes a random walk path as the neighborhood of nodes. In addition, such algorithms only take advantage of the potential features of nodes, but the explicit features of nodes play a good role in link prediction. In this paper, a link prediction method based on deep convolutional neural network is proposed. It constructs a model of the residual attention network to capture the link structure features from the sub-graph. Further study finds that the information flow transmission efficiency of the residual attention mechanism was not high, so a densely convolutional neural network model was proposed for link prediction. We evaluate our proposed method on four published data sets. The results show that our method is better than several other benchmark algorithms on link prediction.

Teknik Data Mining Dalam Clustering Produksi Susu Segar Di Indonesia Dengan Algoritma K-Means

2019 ◽  
Vol 1 (1) ◽  
pp. 31-39
Author(s):  
Ilham Safitra Damanik ◽  
Sundari Retno Andani ◽  
Dedi Sehendro
Keyword(s):  
Data Mining ◽  
Milk Production ◽  
Clustering Algorithm ◽  
Clustering Method ◽  
Data Mining Techniques ◽  
Low Level ◽  
Fresh Milk ◽  
Nutritional Needs ◽  
High Level ◽  
Level Cluster

Milk is an important intake to meet nutritional needs. Both consumed by children, and adults. Indonesia has many producers of fresh milk, but it is not sufficient for national milk needs. Data mining is a science in the field of computers that is widely used in research. one of the data mining techniques is Clustering. Clustering is a method by grouping data. The Clustering method will be more optimal if you use a lot of data. Data to be used are provincial data in Indonesia from 2000 to 2017 obtained from the Central Statistics Agency. The results of this study are in Clusters based on 2 milk-producing groups, namely high-dairy producers and low-milk producing regions. From 27 data on fresh milk production in Indonesia, two high-level provinces can be obtained, namely: West Java and East Java. And 25 others were added in 7 provinces which did not follow the calculation of the K-Means Clustering Algorithm, including in the low level cluster.

Determinants of Abuse of the Bodies of the Dead

2019 ◽  
pp. 71-77
Author(s):  
Margarita Khomyakova
Keyword(s):  
Low Income ◽  
Criminal Code ◽  
Value Judgments ◽  
Legal Norms ◽  
Low Level ◽  
Medical Institutions ◽  
Specific Object ◽  
The Subject ◽  
The Dead ◽  
High Level

The author analyzes definitions of the concepts of determinants of crime given by various scientists and offers her definition. In this study, determinants of crime are understood as a set of its causes, the circumstances that contribute committing them, as well as the dynamics of crime. It is noted that the Russian legislator in Article 244 of the Criminal Code defines the object of this criminal assault as public morality. Despite the use of evaluative concepts both in the disposition of this norm and in determining the specific object of a given crime, the position of criminologists is unequivocal: crimes of this kind are immoral and are in irreconcilable conflict with generally accepted moral and legal norms. In the paper, some views are considered with regard to making value judgments which could hardly apply to legal norms. According to the author, the reasons for abuse of the bodies of the dead include economic problems of the subject of a crime, a low level of culture and legal awareness; this list is not exhaustive. The main circumstances that contribute committing abuse of the bodies of the dead and their burial places are the following: low income and unemployment, low level of criminological prevention, poor maintenance and protection of medical institutions and cemeteries due to underperformance of state and municipal bodies. The list of circumstances is also open-ended. Due to some factors, including a high level of latency, it is not possible to reflect the dynamics of such crimes objectively. At the same time, identification of the determinants of abuse of the bodies of the dead will reduce the number of such crimes.

A Drug Target Interaction Prediction Based on LINE-RF Learning

2020 ◽  
Vol 15 (7) ◽  
pp. 750-757
Author(s):  
Jihong Wang ◽  
Yue Shi ◽  
Xiaodan Wang ◽  
Huiyou Chang
Keyword(s):  
Network Topology ◽  
Drug Target ◽  
Large Scale ◽  
Representation Learning ◽  
New Drugs ◽  
Combination Method ◽  
Learning Methods ◽  
Network Representation ◽  
On Line ◽  
Clinical Experiments

Background: At present, using computer methods to predict drug-target interactions (DTIs) is a very important step in the discovery of new drugs and drug relocation processes. The potential DTIs identified by machine learning methods can provide guidance in biochemical or clinical experiments. Objective: The goal of this article is to combine the latest network representation learning methods for drug-target prediction research, improve model prediction capabilities, and promote new drug development. Methods: We use large-scale information network embedding (LINE) method to extract network topology features of drugs, targets, diseases, etc., integrate features obtained from heterogeneous networks, construct binary classification samples, and use random forest (RF) method to predict DTIs. Results: The experiments in this paper compare the common classifiers of RF, LR, and SVM, as well as the typical network representation learning methods of LINE, Node2Vec, and DeepWalk. It can be seen that the combined method LINE-RF achieves the best results, reaching an AUC of 0.9349 and an AUPR of 0.9016. Conclusion: The learning method based on LINE network can effectively learn drugs, targets, diseases and other hidden features from the network topology. The combination of features learned through multiple networks can enhance the expression ability. RF is an effective method of supervised learning. Therefore, the Line-RF combination method is a widely applicable method.

Sign in / Sign up

Export Citation Format

Share Document