Most existing network representation learning algorithms focus on network structures for learning.However,network structure is only one kind of view and feature for various networks,and it cannot fully reflect all cha...Most existing network representation learning algorithms focus on network structures for learning.However,network structure is only one kind of view and feature for various networks,and it cannot fully reflect all characteristics of networks.In fact,network vertices usually contain rich text information,which can be well utilized to learn text-enhanced network representations.Meanwhile,Matrix-Forest Index(MFI)has shown its high effectiveness and stability in link prediction tasks compared with other algorithms of link prediction.Both MFI and Inductive Matrix Completion(IMC)are not well applied with algorithmic frameworks of typical representation learning methods.Therefore,we proposed a novel semi-supervised algorithm,tri-party deep network representation learning using inductive matrix completion(TDNR).Based on inductive matrix completion algorithm,TDNR incorporates text features,the link certainty degrees of existing edges and the future link probabilities of non-existing edges into network representations.The experimental results demonstrated that TFNR outperforms other baselines on three real-world datasets.The visualizations of TDNR show that proposed algorithm is more discriminative than other unsupervised approaches.展开更多
The homogeneity analysis of multi-airport system can provide important decision-making support for the route layout and cooperative operation.Existing research seldom analyzes the homogeneity of multi-airport system f...The homogeneity analysis of multi-airport system can provide important decision-making support for the route layout and cooperative operation.Existing research seldom analyzes the homogeneity of multi-airport system from the perspective of route network analysis,and the attribute information of airport nodes in the airport route network is not appropriately integrated into the airport network.In order to solve this problem,a multi-airport system homogeneity analysis method based on airport attribute network representation learning is proposed.Firstly,the route network of a multi-airport system with attribute information is constructed.If there are flights between airports,an edge is added between airports,and regional attribute information is added for each airport node.Secondly,the airport attributes and the airport network vector are represented respectively.The airport attributes and the airport network vector are embedded into the unified airport representation vector space by the network representation learning method,and then the airport vector integrating the airport attributes and the airport network characteristics is obtained.By calculating the similarity of the airport vectors,it is convenient to calculate the degree of homogeneity between airports and the homogeneity of the multi-airport system.The experimental results on the Beijing-Tianjin-Hebei multi-airport system show that,compared with other existing algorithms,the homogeneity analysis method based on attributed network representation learning can get more consistent results with the current situation of Beijing-Tianjin-Hebei multi-airport system.展开更多
Blockchain platform swith the unique characteristics of anonymity,decentralization,and transparency of their transactions,which are faced with abnormal activities such as money laundering,phishing scams,and fraudulent...Blockchain platform swith the unique characteristics of anonymity,decentralization,and transparency of their transactions,which are faced with abnormal activities such as money laundering,phishing scams,and fraudulent behavior,posing a serious threat to account asset security.For these potential security risks,this paper proposes a hybrid neural network detection method(HNND)that learns multiple types of account features and enhances fusion information among them to effectively detect abnormal transaction behaviors in the blockchain.In HNND,the Temporal Transaction Graph Attention Network(T2GAT)is first designed to learn biased aggregation representation of multi-attribute transactions among nodes,which can capture key temporal information from node neighborhood transactions.Then,the Graph Convolutional Network(GCN)is adopted which captures abstract structural features of the transaction network.Further,the Stacked Denoising Autoencode(SDA)is developed to achieve adaptive fusion of thses features from different modules.Moreover,the SDA enhances robustness and generalization ability of node representation,leading to higher binary classification accuracy in detecting abnormal behaviors of blockchain accounts.Evaluations on a real-world abnormal transaction dataset demonstrate great advantages of the proposed HNND method over other compared methods.展开更多
Network representation learning called NRL for short aims at embedding various networks into low-dimensional continuous distributed vector spaces.Most existing representation learning methods focus on learning represe...Network representation learning called NRL for short aims at embedding various networks into low-dimensional continuous distributed vector spaces.Most existing representation learning methods focus on learning representations purely based on the network topology.i.e.,the linkage relationships between network nodes,but the nodes in lots of networks may contain rich text features,which are beneficial to network analysis tasks,such as node classification,link prediction and so on.In this paper,we propose a novel network representation learning model,which is named as Text-Enhanced Network Representation Learning called TENR for short,by introducing text features of the nodesto learn more discriminative network representations,which come from joint learning of both the network topology and text features,and include common influencing factors of both parties.In the experiments,we evaluate our proposed method and other baseline methods on the task of node classihication.The experimental results demonstrate that our method outperforms other baseline methods on three real-world datasets.展开更多
Network representation learning algorithms,which aim at automatically encoding graphs into low-dimensional vector representations with a variety of node similarity definitions,have a wide range of downstream applicati...Network representation learning algorithms,which aim at automatically encoding graphs into low-dimensional vector representations with a variety of node similarity definitions,have a wide range of downstream applications.Most existing methods either have low accuracies in downstream tasks or a very limited application field,such as article classification in citation networks.In this paper,we propose a novel network representation method,named Link Prediction based Network Representation(LPNR),which generalizes the latest graph neural network and optimizes a carefully designed objective function that preserves linkage structures.LPNR can not only learn meaningful node representations that achieve competitive accuracy in node centrality measurement and community detection but also achieve high accuracy in the link prediction task.Experiments prove the effectiveness of LPNR on three real-world networks.With the mini-batch and fixed sampling strategy,LPNR can learn the embedding of large graphs in a few hours.展开更多
Cryptocurrency, as a typical application scene of blockchain, has attracted broad interests from both industrial and academic communities. With its rapid development, the cryptocurrency transaction network embedding(C...Cryptocurrency, as a typical application scene of blockchain, has attracted broad interests from both industrial and academic communities. With its rapid development, the cryptocurrency transaction network embedding(CTNE) has become a hot topic. It embeds transaction nodes into low-dimensional feature space while effectively maintaining a network structure,thereby discovering desired patterns demonstrating involved users' normal and abnormal behaviors. Based on a wide investigation into the state-of-the-art CTNE, this survey has made the following efforts: 1) categorizing recent progress of CTNE methods, 2) summarizing the publicly available cryptocurrency transaction network datasets, 3) evaluating several widely-adopted methods to show their performance in several typical evaluation protocols, and 4) discussing the future trends of CTNE. By doing so, it strives to provide a systematic and comprehensive overview of existing CTNE methods from static to dynamic perspectives,thereby promoting further research into this emerging and important field.展开更多
Malicious social robots are the disseminators of malicious information on social networks,which seriously affect information security and network environments.Efficient and reliable classification of social robots is ...Malicious social robots are the disseminators of malicious information on social networks,which seriously affect information security and network environments.Efficient and reliable classification of social robots is crucial for detecting information manipulation in social networks.Supervised classification based on manual feature extraction has been widely used in social robot detection.However,these methods not only involve the privacy of users but also ignore hidden feature information,especially the graph feature,and the label utilization rate of semi-supervised algorithms is low.Aiming at the problems of shallow feature extraction and low label utilization rate in existing social network robot detection methods,in this paper a robot detection scheme based on weighted network topology is proposed,which introduces an improved network representation learning algorithm to extract the local structure features of the network,and combined with the graph convolution network(GCN)algorithm based on the graph filter,to obtain the global structure features of the network.An end-to-end semi-supervised combination model(Semi-GSGCN)is established to detect malicious social robots.Experiments on a social network dataset(cresci-rtbust-2019)show that the proposed method has high versatility and effectiveness in detecting social robots.In addition,this method has a stronger insight into robots in social networks than other methods.展开更多
Interactivity is the most significant feature of network data,especially in social networks.Existing network embedding methods have achieved remarkable results in learning network structure and node attributes,but do ...Interactivity is the most significant feature of network data,especially in social networks.Existing network embedding methods have achieved remarkable results in learning network structure and node attributes,but do not pay attention to the multi-interaction between nodes,which limits the extraction and mining of potential deep interactions between nodes.To tackle the problem,we propose a method called Multi-Interaction heterogeneous information Network Embedding(MINE).Firstly,we introduced the multi-interactions heterogeneous information network and extracted complex heterogeneous relation sequences by the multi-interaction extraction algorithm.Secondly,we use a well-designed multi-relationship network fusion model based on the attention mechanism to fuse multiple interactional relationships.Finally,applying a multitasking model makes the learned vector contain richer semantic relationships.A large number of practical experiments prove that our proposed method outperforms existing methods on multiple data sets.展开更多
Many network presentation learning algorithms(NPLA)have originated from the process of the random walk between nodes in recent years.Despite these algorithms can obtain great embedding results,there may be also some l...Many network presentation learning algorithms(NPLA)have originated from the process of the random walk between nodes in recent years.Despite these algorithms can obtain great embedding results,there may be also some limitations.For instance,only the structural information of nodes is considered when these kinds of algorithms are constructed.Aiming at this issue,a label and community information-based network presentation learning algorithm(LC-NPLA)is proposed in this paper.First of all,by using the community information and the label information of nodes,the first-order neighbors of nodes are reconstructed.In the next,the random walk strategy is improved by integrating the degree information and label information of nodes.Then,the node sequence obtained from random walk sampling is transformed into the node representation vector by the Skip-Gram model.At last,the experimental results on ten real-world networks demonstrate that the proposed algorithm has great advantages in the label classification,network reconstruction and link prediction tasks,compared with three benchmark algorithms.展开更多
Modeling and analysis of complex social networks is an important topic in social computing.Graph convolutional networks(GCNs)are widely used for learning social network embeddings and social network analysis.However,r...Modeling and analysis of complex social networks is an important topic in social computing.Graph convolutional networks(GCNs)are widely used for learning social network embeddings and social network analysis.However,real-world complex social networks,such as Facebook and Math,exhibit significant global structural and dynamic characteristics that are not adequately captured by conventional GCN models.To address the above issues,this paper proposes a novel graph convolutional network considering global structural features and global temporal dependencies(GSTGCN).Specifically,we innovatively design a graph coarsening strategy based on the importance of social membership to construct a dynamic diffusion process of graphs.This dynamic diffusion process can be viewed as using higher-order subgraph embeddings to guide the generation of lower-order subgraph embeddings,and we model this process using gate recurrent unit(GRU)to extract comprehensive global structural features of the graph and the evolutionary processes embedded among subgraphs.Furthermore,we design a new evolutionary strategy that incorporates a temporal self-attention mechanism to enhance the extraction of global temporal dependencies of dynamic networks by GRU.GSTGCN outperforms current state-of-the-art network embedding methods in important social networks tasks such as link prediction and financial fraud identification.展开更多
Complex systems in the real world often can be modeled as network structures,and community discovery algorithms for complex networks enable researchers to understand the internal structure and implicit information of ...Complex systems in the real world often can be modeled as network structures,and community discovery algorithms for complex networks enable researchers to understand the internal structure and implicit information of networks.Existing community discovery algorithms are usually designed for single-layer networks or single-interaction relationships and do not consider the attribute information of nodes.However,many real-world networks consist of multiple types of nodes and edges,and there may be rich semantic information on nodes and edges.The methods for single-layer networks cannot effectively tackle multi-layer information,multi-relationship information,and attribute information.This paper proposes a community discovery algorithm based on multi-relationship embedding.The proposed algorithm first models the nodes in the network to obtain the embedding matrix for each node relationship type and generates the node embedding matrix for each specific relationship type in the network by node encoder.The node embedding matrix is provided as input for aggregating the node embedding matrix of each specific relationship type using a Graph Convolutional Network(GCN)to obtain the final node embedding matrix.This strategy allows capturing of rich structural and attributes information in multi-relational networks.Experiments were conducted on different datasets with baselines,and the results show that the proposed algorithm obtains significant performance improvement in community discovery,node clustering,and similarity search tasks,and compared to the baseline with the best performance,the proposed algorithm achieves an average improvement of 3.1%on Macro-F1 and 4.7%on Micro-F1,which proves the effectiveness of the proposed algorithm.展开更多
Background:Heterogeneous network-based methods are powerful analytical tools for many real-world data mining tasks in biomedical field.The specific aim of this survey is to examine the representative algorithms used i...Background:Heterogeneous network-based methods are powerful analytical tools for many real-world data mining tasks in biomedical field.The specific aim of this survey is to examine the representative algorithms used in heterogeneous network data mining tasks and concentrate on biomedical domain to analyze the application of these techniques in the real world.Methods:This study is a review.In this study,keywords of heterogeneous network-based algorithms were used to search in CNKI and Web of Science databases,and the results were manually analyzed.Among these results,100 key papers most relevant to heterogeneous network-based algorithms in the biomedical data mining were selected for review.Through the review of the research literature,we first introduce the basic concepts and some challenges in this field;then we provide two taxonomies of existing heterogeneous network representation learning algorithms from technical and feature perspectives;meanwhile,we also systemically summarize research developments of heterogeneous network generation algorithms.In addition,we further present major data mining tasks in the real-world application of biomedical domain.Finally,we explore the advanced topics and forecast the future research directions of heterogeneous networks.Findings:The heterogeneous network-based algorithms are analyzed from technical perspective.The detailed analysis of these algorithms contributes to a deeper understanding of their features and applicability,and promotes their use in data mining tasks.The analysis of the application of these algorithms in biomedical research help advance biomedical research from the molecular level to the healthcare system.Deep learning frameworks are the current focus of these algorithms.Interpretation:This survey helps the understanding of heterogeneous network algorithms and envisions to provide a universal reference and guideline for heterogeneous network data mining tasks in the field of biomedicine.展开更多
基金Projects(11661069,61763041) supported by the National Natural Science Foundation of ChinaProject(IRT_15R40) supported by Changjiang Scholars and Innovative Research Team in University,ChinaProject(2017TS045) supported by the Fundamental Research Funds for the Central Universities,China
文摘Most existing network representation learning algorithms focus on network structures for learning.However,network structure is only one kind of view and feature for various networks,and it cannot fully reflect all characteristics of networks.In fact,network vertices usually contain rich text information,which can be well utilized to learn text-enhanced network representations.Meanwhile,Matrix-Forest Index(MFI)has shown its high effectiveness and stability in link prediction tasks compared with other algorithms of link prediction.Both MFI and Inductive Matrix Completion(IMC)are not well applied with algorithmic frameworks of typical representation learning methods.Therefore,we proposed a novel semi-supervised algorithm,tri-party deep network representation learning using inductive matrix completion(TDNR).Based on inductive matrix completion algorithm,TDNR incorporates text features,the link certainty degrees of existing edges and the future link probabilities of non-existing edges into network representations.The experimental results demonstrated that TFNR outperforms other baselines on three real-world datasets.The visualizations of TDNR show that proposed algorithm is more discriminative than other unsupervised approaches.
基金supported by the Natural Science Foundation of Tianjin(No.20JCQNJC00720)the Fundamental Research Fund for the Central Universities(No.3122021052)。
文摘The homogeneity analysis of multi-airport system can provide important decision-making support for the route layout and cooperative operation.Existing research seldom analyzes the homogeneity of multi-airport system from the perspective of route network analysis,and the attribute information of airport nodes in the airport route network is not appropriately integrated into the airport network.In order to solve this problem,a multi-airport system homogeneity analysis method based on airport attribute network representation learning is proposed.Firstly,the route network of a multi-airport system with attribute information is constructed.If there are flights between airports,an edge is added between airports,and regional attribute information is added for each airport node.Secondly,the airport attributes and the airport network vector are represented respectively.The airport attributes and the airport network vector are embedded into the unified airport representation vector space by the network representation learning method,and then the airport vector integrating the airport attributes and the airport network characteristics is obtained.By calculating the similarity of the airport vectors,it is convenient to calculate the degree of homogeneity between airports and the homogeneity of the multi-airport system.The experimental results on the Beijing-Tianjin-Hebei multi-airport system show that,compared with other existing algorithms,the homogeneity analysis method based on attributed network representation learning can get more consistent results with the current situation of Beijing-Tianjin-Hebei multi-airport system.
文摘Blockchain platform swith the unique characteristics of anonymity,decentralization,and transparency of their transactions,which are faced with abnormal activities such as money laundering,phishing scams,and fraudulent behavior,posing a serious threat to account asset security.For these potential security risks,this paper proposes a hybrid neural network detection method(HNND)that learns multiple types of account features and enhances fusion information among them to effectively detect abnormal transaction behaviors in the blockchain.In HNND,the Temporal Transaction Graph Attention Network(T2GAT)is first designed to learn biased aggregation representation of multi-attribute transactions among nodes,which can capture key temporal information from node neighborhood transactions.Then,the Graph Convolutional Network(GCN)is adopted which captures abstract structural features of the transaction network.Further,the Stacked Denoising Autoencode(SDA)is developed to achieve adaptive fusion of thses features from different modules.Moreover,the SDA enhances robustness and generalization ability of node representation,leading to higher binary classification accuracy in detecting abnormal behaviors of blockchain accounts.Evaluations on a real-world abnormal transaction dataset demonstrate great advantages of the proposed HNND method over other compared methods.
基金supported by the National Natural Sci-ence Foundation of China(Grant Nos.11661069 and 61763041)the Pro-gram for Changjiang Scholars and Innovative Research Team in Universities(IRT_15R40).
文摘Network representation learning called NRL for short aims at embedding various networks into low-dimensional continuous distributed vector spaces.Most existing representation learning methods focus on learning representations purely based on the network topology.i.e.,the linkage relationships between network nodes,but the nodes in lots of networks may contain rich text features,which are beneficial to network analysis tasks,such as node classification,link prediction and so on.In this paper,we propose a novel network representation learning model,which is named as Text-Enhanced Network Representation Learning called TENR for short,by introducing text features of the nodesto learn more discriminative network representations,which come from joint learning of both the network topology and text features,and include common influencing factors of both parties.In the experiments,we evaluate our proposed method and other baseline methods on the task of node classihication.The experimental results demonstrate that our method outperforms other baseline methods on three real-world datasets.
基金support from the program of the China Scholarships Council(No.201806040107)the Fundamental Research Funds for the Central Universities,the National Natural Science Foundation of China(Nos.61673070 and 61903020)the BUCT Talent Start-up Fund(No.BUCTRC 201825).We acknowledge the help from the Swarma Club.
文摘Network representation learning algorithms,which aim at automatically encoding graphs into low-dimensional vector representations with a variety of node similarity definitions,have a wide range of downstream applications.Most existing methods either have low accuracies in downstream tasks or a very limited application field,such as article classification in citation networks.In this paper,we propose a novel network representation method,named Link Prediction based Network Representation(LPNR),which generalizes the latest graph neural network and optimizes a carefully designed objective function that preserves linkage structures.LPNR can not only learn meaningful node representations that achieve competitive accuracy in node centrality measurement and community detection but also achieve high accuracy in the link prediction task.Experiments prove the effectiveness of LPNR on three real-world networks.With the mini-batch and fixed sampling strategy,LPNR can learn the embedding of large graphs in a few hours.
基金supported in part by the National Natural Science Foundation of China (62272078)the CAAI-Huawei MindSpore Open Fund (CAAIXSJLJJ-2021-035A)the Doctoral Student Talent Training Program of Chongqing University of Posts and Telecommunications (BYJS202009)。
文摘Cryptocurrency, as a typical application scene of blockchain, has attracted broad interests from both industrial and academic communities. With its rapid development, the cryptocurrency transaction network embedding(CTNE) has become a hot topic. It embeds transaction nodes into low-dimensional feature space while effectively maintaining a network structure,thereby discovering desired patterns demonstrating involved users' normal and abnormal behaviors. Based on a wide investigation into the state-of-the-art CTNE, this survey has made the following efforts: 1) categorizing recent progress of CTNE methods, 2) summarizing the publicly available cryptocurrency transaction network datasets, 3) evaluating several widely-adopted methods to show their performance in several typical evaluation protocols, and 4) discussing the future trends of CTNE. By doing so, it strives to provide a systematic and comprehensive overview of existing CTNE methods from static to dynamic perspectives,thereby promoting further research into this emerging and important field.
基金This research was funded by the National Key R&D Program of China[Grant Number 2017YFB0802703]Beijing Natural Science Foundation[Grant Number 4202002]+1 种基金the research project of the Department of Computer Science in BJUT[Grant Number 2019JSJKY004]Beijing Municipal Postdoc Science Foundation[No Grant Number]and Beijing Chaoyang District Postdoc Science Foundation[No Grant Number].
文摘Malicious social robots are the disseminators of malicious information on social networks,which seriously affect information security and network environments.Efficient and reliable classification of social robots is crucial for detecting information manipulation in social networks.Supervised classification based on manual feature extraction has been widely used in social robot detection.However,these methods not only involve the privacy of users but also ignore hidden feature information,especially the graph feature,and the label utilization rate of semi-supervised algorithms is low.Aiming at the problems of shallow feature extraction and low label utilization rate in existing social network robot detection methods,in this paper a robot detection scheme based on weighted network topology is proposed,which introduces an improved network representation learning algorithm to extract the local structure features of the network,and combined with the graph convolution network(GCN)algorithm based on the graph filter,to obtain the global structure features of the network.An end-to-end semi-supervised combination model(Semi-GSGCN)is established to detect malicious social robots.Experiments on a social network dataset(cresci-rtbust-2019)show that the proposed method has high versatility and effectiveness in detecting social robots.In addition,this method has a stronger insight into robots in social networks than other methods.
基金This work is supported by the Fundamental Research Funds for the Central Universities(Grant No.HIT.NSRIF.201714)Weihai Science and Technology Development Program(2016DXGJMS15)Key Research and Development Program in Shandong Provincial(2017GGX90103).
文摘Interactivity is the most significant feature of network data,especially in social networks.Existing network embedding methods have achieved remarkable results in learning network structure and node attributes,but do not pay attention to the multi-interaction between nodes,which limits the extraction and mining of potential deep interactions between nodes.To tackle the problem,we propose a method called Multi-Interaction heterogeneous information Network Embedding(MINE).Firstly,we introduced the multi-interactions heterogeneous information network and extracted complex heterogeneous relation sequences by the multi-interaction extraction algorithm.Secondly,we use a well-designed multi-relationship network fusion model based on the attention mechanism to fuse multiple interactional relationships.Finally,applying a multitasking model makes the learned vector contain richer semantic relationships.A large number of practical experiments prove that our proposed method outperforms existing methods on multiple data sets.
基金What is more,we thank the National Natural Science Foundation of China(Nos.61966039,62241604)the Scientific Research Fund Project of the Education Department of Yunnan Province(No.2023Y0565)Also,this work was supported in part by the Xingdian Talent Support Program for Young Talents(No.XDYC-QNRC-2022-0518).
文摘Many network presentation learning algorithms(NPLA)have originated from the process of the random walk between nodes in recent years.Despite these algorithms can obtain great embedding results,there may be also some limitations.For instance,only the structural information of nodes is considered when these kinds of algorithms are constructed.Aiming at this issue,a label and community information-based network presentation learning algorithm(LC-NPLA)is proposed in this paper.First of all,by using the community information and the label information of nodes,the first-order neighbors of nodes are reconstructed.In the next,the random walk strategy is improved by integrating the degree information and label information of nodes.Then,the node sequence obtained from random walk sampling is transformed into the node representation vector by the Skip-Gram model.At last,the experimental results on ten real-world networks demonstrate that the proposed algorithm has great advantages in the label classification,network reconstruction and link prediction tasks,compared with three benchmark algorithms.
基金supported by the National Natural Science Foundation of China(Nos.62002063 and U21A20472)Natural Science Foundation of Fujian Province(Nos.2020J05112 and 2022J01118)+1 种基金National Key Research and Development Plan of China(No.2021YFB3600503)Major Science and Technology Project of Fujian Province(No.2021HZ022007).
文摘Modeling and analysis of complex social networks is an important topic in social computing.Graph convolutional networks(GCNs)are widely used for learning social network embeddings and social network analysis.However,real-world complex social networks,such as Facebook and Math,exhibit significant global structural and dynamic characteristics that are not adequately captured by conventional GCN models.To address the above issues,this paper proposes a novel graph convolutional network considering global structural features and global temporal dependencies(GSTGCN).Specifically,we innovatively design a graph coarsening strategy based on the importance of social membership to construct a dynamic diffusion process of graphs.This dynamic diffusion process can be viewed as using higher-order subgraph embeddings to guide the generation of lower-order subgraph embeddings,and we model this process using gate recurrent unit(GRU)to extract comprehensive global structural features of the graph and the evolutionary processes embedded among subgraphs.Furthermore,we design a new evolutionary strategy that incorporates a temporal self-attention mechanism to enhance the extraction of global temporal dependencies of dynamic networks by GRU.GSTGCN outperforms current state-of-the-art network embedding methods in important social networks tasks such as link prediction and financial fraud identification.
基金This work was supported by the Key Technologies Research and Development Program of Liaoning Province in China under Grant 2021JH1/10400079the Fundamental Research Funds for the Central Universities under Grant 2217002.
文摘Complex systems in the real world often can be modeled as network structures,and community discovery algorithms for complex networks enable researchers to understand the internal structure and implicit information of networks.Existing community discovery algorithms are usually designed for single-layer networks or single-interaction relationships and do not consider the attribute information of nodes.However,many real-world networks consist of multiple types of nodes and edges,and there may be rich semantic information on nodes and edges.The methods for single-layer networks cannot effectively tackle multi-layer information,multi-relationship information,and attribute information.This paper proposes a community discovery algorithm based on multi-relationship embedding.The proposed algorithm first models the nodes in the network to obtain the embedding matrix for each node relationship type and generates the node embedding matrix for each specific relationship type in the network by node encoder.The node embedding matrix is provided as input for aggregating the node embedding matrix of each specific relationship type using a Graph Convolutional Network(GCN)to obtain the final node embedding matrix.This strategy allows capturing of rich structural and attributes information in multi-relational networks.Experiments were conducted on different datasets with baselines,and the results show that the proposed algorithm obtains significant performance improvement in community discovery,node clustering,and similarity search tasks,and compared to the baseline with the best performance,the proposed algorithm achieves an average improvement of 3.1%on Macro-F1 and 4.7%on Micro-F1,which proves the effectiveness of the proposed algorithm.
基金funded by the“Biomedical Literature Information Assurance and Integrated Service Platform”,a Major Collaborative Innovation Project of Medical and Health Technology Innovation Project of Chinese Academy of Medical Sciences in 2021,grant number 2021-I2M-1-033.
文摘Background:Heterogeneous network-based methods are powerful analytical tools for many real-world data mining tasks in biomedical field.The specific aim of this survey is to examine the representative algorithms used in heterogeneous network data mining tasks and concentrate on biomedical domain to analyze the application of these techniques in the real world.Methods:This study is a review.In this study,keywords of heterogeneous network-based algorithms were used to search in CNKI and Web of Science databases,and the results were manually analyzed.Among these results,100 key papers most relevant to heterogeneous network-based algorithms in the biomedical data mining were selected for review.Through the review of the research literature,we first introduce the basic concepts and some challenges in this field;then we provide two taxonomies of existing heterogeneous network representation learning algorithms from technical and feature perspectives;meanwhile,we also systemically summarize research developments of heterogeneous network generation algorithms.In addition,we further present major data mining tasks in the real-world application of biomedical domain.Finally,we explore the advanced topics and forecast the future research directions of heterogeneous networks.Findings:The heterogeneous network-based algorithms are analyzed from technical perspective.The detailed analysis of these algorithms contributes to a deeper understanding of their features and applicability,and promotes their use in data mining tasks.The analysis of the application of these algorithms in biomedical research help advance biomedical research from the molecular level to the healthcare system.Deep learning frameworks are the current focus of these algorithms.Interpretation:This survey helps the understanding of heterogeneous network algorithms and envisions to provide a universal reference and guideline for heterogeneous network data mining tasks in the field of biomedicine.
