Due to its anonymity and decentralization,Bitcoin has long been a haven for various illegal activities.Cybercriminals generally legalize illicit funds by Bitcoin mixing services.Therefore,it is critical to investigate...Due to its anonymity and decentralization,Bitcoin has long been a haven for various illegal activities.Cybercriminals generally legalize illicit funds by Bitcoin mixing services.Therefore,it is critical to investigate the mixing services in cryptocurrency anti-money laundering.Existing studies treat different mixing services as a class of suspicious Bitcoin entities.Furthermore,they are limited by relying on expert experience or needing to deal with large-scale networks.So far,multi-class mixing service identification has not been explored yet.It is challenging since mixing services share a similar procedure,presenting no sharp distinctions.However,mixing service identification facilitates the healthy development of Bitcoin,supports financial forensics for cryptocurrency regulation and legislation,and provides technical means for fine-grained blockchain supervision.This paper aims to achieve multi-class Bitcoin Mixing Service Identification with a Graph Classification(BMSI-GC)model.First,BMSI-GC constructs 2-hop ego networks(2-egonets)of mixing services based on their historical transactions.Second,it applies graph2vec,a graph classification model mainly used to calculate the similarity between graphs,to automatically extract address features from the constructed 2-egonets.Finally,it trains a multilayer perceptron classifier to perform classification based on the extracted features.BMSI-GC is flexible without handling the full-size network and handcrafting address features.Moreover,the differences in transaction patterns of mixing services reflected in the 2-egonets provide adequate information for identification.Our experimental study demonstrates that BMSI-GC performs excellently in multi-class Bitcoin mixing service identification,achieving an average identification F1-score of 95.08%.展开更多
Graph-based image classification has emerged as a powerful alternative to traditional convolutional approaches,leveraging the relational structure between image regions to improve accuracy.This paper presents an enhan...Graph-based image classification has emerged as a powerful alternative to traditional convolutional approaches,leveraging the relational structure between image regions to improve accuracy.This paper presents an enhanced graph-based image classification framework that integrates convolutional neural network(CNN)features with graph convolutional network(GCN)learning,leveraging superpixel-based image representations.The proposed framework initiates the process by segmenting input images into significant superpixels,reducing computational complexity while preserving essential spatial structures.A pre-trained CNN backbone extracts both global and local features from these superpixels,capturing critical texture and shape information.These features are structured into a graph,and the framework presents a graph classification model that learns and propagates relationships between nodes,improving global contextual understanding.By combining the strengths of CNN-based feature extraction and graph-based relational learning,the method achieves higher accuracy,faster training speeds,and greater robustness in image classification tasks.Experimental evaluations on four agricultural datasets demonstrate the proposed model’s superior performance,achieving accuracy rates of 96.57%,99.63%,95.19%,and 90.00%on Tomato Leaf Disease,Dragon Fruit,Tomato Ripeness,and Dragon Fruit and Leaf datasets,respectively.The model consistently outperforms conventional CNN(89.27%–94.23%accuracy),VIT(89.45%–99.77%accuracy),VGG16(93.97%–99.52%accuracy),and ResNet50(86.67%–99.26%accuracy)methods across all datasets,with particularly significant improvements on challenging datasets such as Tomato Ripeness(95.19%vs.86.67%–94.44%)and Dragon Fruit and Leaf(90.00%vs.82.22%–83.97%).The compact superpixel representation and efficient feature propagation mechanism further accelerate learning compared to traditional CNN and graph-based approaches.展开更多
Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.Howev...Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.However,despite their success,GNNs remain vulnerable to adversarial attacks that can significantly degrade their classification accuracy.Existing adversarial attack strategies primarily rely on label information to guide the attacks,which limits their applicability in scenarios where such information is scarce or unavailable.This paper introduces an innovative unsupervised attack method for graph classification,which operates without relying on label information,thereby enhancing its applicability in a broad range of scenarios.Specifically,our method first leverages a graph contrastive learning loss to learn high-quality graph embeddings by comparing different stochastic augmented views of the graphs.To effectively perturb the graphs,we then introduce an implicit estimator that measures the impact of various modifications on graph structures.The proposed strategy identifies and flips edges with the top-K highest scores,determined by the estimator,to maximize the degradation of the model’s performance.In addition,to defend against such attack,we propose a lightweight regularization-based defense mechanism that is specifically tailored to mitigate the structural perturbations introduced by our attack strategy.It enhances model robustness by enforcing embedding consistency and edge-level smoothness during training.We conduct experiments on six public TU graph classification datasets:NCI1,NCI109,Mutagenicity,ENZYMES,COLLAB,and DBLP_v1,to evaluate the effectiveness of our attack and defense strategies.Under an attack budget of 3,the maximum reduction in model accuracy reaches 6.67%on the Graph Convolutional Network(GCN)and 11.67%on the Graph Attention Network(GAT)across different datasets,indicating that our unsupervised method induces degradation comparable to state-of-the-art supervised attacks.Meanwhile,our defense achieves the highest accuracy recovery of 3.89%(GCN)and 5.00%(GAT),demonstrating improved robustness against structural perturbations.展开更多
Graph neural networks(GNNs)have achieved state-of-the-art performance on graph classification tasks,which aim to pre-dict the class labels of entire graphs and have widespread applications.However,existing GNN based m...Graph neural networks(GNNs)have achieved state-of-the-art performance on graph classification tasks,which aim to pre-dict the class labels of entire graphs and have widespread applications.However,existing GNN based methods for graph classification are data-hungry and ignore the fact that labeling graph examples is extremely expensive due to the intrinsic complexity.More import-antly,real-world graph data are often scattered in different locations.Motivated by these observations,this article presents federated collaborative graph neural networks for few-shot graph classification,termed FCGNN.With its owned graph examples,each client first trains two branches to collaboratively characterize each graph from different views and obtains a high-quality local few-shot graph learn-ing model that can generalize to novel categories not seen while training.In each branch,initial graph embeddings are extracted by any GNN and the relation information among graph examples is incorporated to produce refined graph representations via relation aggrega-tion layers for few-shot graph classification,which can reduce over-fitting while learning with scarce labeled graph examples.Finally,multiple clients owning graph data unitedly train the few-shot graph classification models with better generalization ability and effect-ively tackle the graph data island issue.Extensive experimental results on few-shot graph classification benchmarks demonstrate the ef-fectiveness and superiority of our proposed framework.展开更多
Graphs are used in various disciplines such as telecommunication,biological networks,as well as social networks.In large-scale networks,it is challenging to detect the communities by learning the distinct properties o...Graphs are used in various disciplines such as telecommunication,biological networks,as well as social networks.In large-scale networks,it is challenging to detect the communities by learning the distinct properties of the graph.As deep learning hasmade contributions in a variety of domains,we try to use deep learning techniques to mine the knowledge from large-scale graph networks.In this paper,we aim to provide a strategy for detecting communities using deep autoencoders and obtain generic neural attention to graphs.The advantages of neural attention are widely seen in the field of NLP and computer vision,which has low computational complexity for large-scale graphs.The contributions of the paper are summarized as follows.Firstly,a transformer is utilized to downsample the first-order proximities of the graph into a latent space,which can result in the structural properties and eventually assist in detecting the communities.Secondly,the fine-tuning task is conducted by tuning variant hyperparameters cautiously,which is applied to multiple social networks(Facebook and Twitch).Furthermore,the objective function(crossentropy)is tuned by L0 regularization.Lastly,the reconstructed model forms communities that present the relationship between the groups.The proposed robust model provides good generalization and is applicable to obtaining not only the community structures in social networks but also the node classification.The proposed graph-transformer shows advanced performance on the social networks with the average NMIs of 0.67±0.04,0.198±0.02,0.228±0.02,and 0.68±0.03 on Wikipedia crocodiles,Github Developers,Twitch England,and Facebook Page-Page networks,respectively.展开更多
We introduce the triple crossing number, a variation of the crossing number, of a graph, which is the minimal number of crossing points in all drawings of the graph with only triple crossings. It is defined to be zero...We introduce the triple crossing number, a variation of the crossing number, of a graph, which is the minimal number of crossing points in all drawings of the graph with only triple crossings. It is defined to be zero for planar graphs, and to be infinite for non-planar graphs which do not admit a drawing with only triple crossings. In this paper, we determine the triple crossing numbers for all complete multipartite graphs which include all complete graphs.展开更多
Emotional electroencephalography(EEG)signals are a primary means of recording emotional brain activity.Currently,the most effective methods for analyzing emotional EEG signals involve feature engineering and neural ne...Emotional electroencephalography(EEG)signals are a primary means of recording emotional brain activity.Currently,the most effective methods for analyzing emotional EEG signals involve feature engineering and neural networks.However,neural networks possess a strong ability for automatic feature extraction.Is it possible to discard feature engineering and directly employ neural networks for end-to-end recognition?Based on the characteristics of EEG signals,this paper proposes an end-to-end feature extraction and classification method for a dynamic self-attention network(DySAT).The study reveals significant differences in brain activity patterns associated with different emotions across various experimenters and time periods.The results of this experiment can provide insights into the reasons behind these differences.展开更多
Given a distribution of pebbles on the vertices of a connected graph G,a pebbling move on G consists of taking two pebbles off one vertex and placing one on an adjacent vertex.Rubbling is a version of pebbling where a...Given a distribution of pebbles on the vertices of a connected graph G,a pebbling move on G consists of taking two pebbles off one vertex and placing one on an adjacent vertex.Rubbling is a version of pebbling where an additional move is allowed.In this new move,one pebble each is removed at vertices u and w that are adjacent to a vertex v,and an extra pebble is added at vertex v.The rubbling number of G,denoted byρ(G),is the smallest number m such that for every distribution of m pebbles on G and every vertex v,at least one pebble can be moved to v by a sequence of rubbling moves.The optimal rubbling number of G,denoted byρopt(G),is the smallest number k such that for some distribution of k pebbles on G,one pebble can be moved to any vertex of G.In this paper,we determineρ(G)for a non-complete bipartite graph G∈B(s,t)with,give an upper bound ofρ(G)for G∈B(s,t)withδ(G)≥[2s+1/3],give an upper bound ofρ(G)for G∈B(s,t),withδ(G)≥[s+1/2],and also obtainρopt(G)for a non-complete bipartite graph G∈B(s,t)withδ(G)≥[s+1/2],where B(s,t)is the set of all connected bipartite graphs with partite sets of size s and t(s≥t)andδ(G)is the minimum degree of G.展开更多
This paper proposes an algorithm applied in se mantic P2P network based on the description logics with the purpose for realizing the concepts distribution of resources, which makes the resources semantic locating easy...This paper proposes an algorithm applied in se mantic P2P network based on the description logics with the purpose for realizing the concepts distribution of resources, which makes the resources semantic locating easy. With the idea of the consistent hashing in the Chord, our algorithm stores the addresses and resources with the values of the same type to select instance. In addition, each peer has its own ontology, which will be completed by the knowledge distributed over the network during the exchange of CHGs （classification hierarchy graphs）. The hierarchy classification of concepts allows to find matching resource by querying to the upper level concept because the all concepts described in the CHG have the same root.展开更多
The prediction of molecular properties is a fundamental task in the field of drug discovery.Recently,graph neural networks(GNNs)have been gaining prominence in this area.Since a molecule tends to have multiple correla...The prediction of molecular properties is a fundamental task in the field of drug discovery.Recently,graph neural networks(GNNs)have been gaining prominence in this area.Since a molecule tends to have multiple correlated properties,there is a great need to develop the multi-task learning ability of GNNs.However,limited by expensive and time-consuming human annotations,collecting complete labels for each task is difficult.As a result,most existing benchmarks involve many missing labels in training data,and the performance of GNNs is impaired due to the lack of sufficient supervision information.To overcome this obstacle,we propose to improve multi-task molecular property prediction by missing label imputation.Specifically,a bipartite graph is first introduced to model the molecule-task co-occurrence relationships.Then,the imputation of missing labels is transformed into predicting missing edges on this bipartite graph.To predict the missing edges,a graph neural network is devised,which can learn the complex molecule-task co-occurrence relationships.After that,we select reliable pseudo labels according to the uncertainty of the prediction results.Boosting with enough and reliable supervision information,our approach achieves state-of-the-art performance on a variety of real-world datasets.展开更多
An f-coloring of a graph G is an edge-coloring of G such that each color appears at each vertex v V（G） at most f（v） times. The minimum number of colors needed to f-color G is called the f-chromatic index of G and...An f-coloring of a graph G is an edge-coloring of G such that each color appears at each vertex v V（G） at most f（v） times. The minimum number of colors needed to f-color G is called the f-chromatic index of G and is denoted by X′f（G）. Any simple graph G has the f-chromatic index equal to △f（G） or △f（G） ＋ 1, where △f（G） =max v V（G）{[d（v）/f（v）]}. If X′f（G） = △f（G）, then G is of f-class 1; otherwise G is of f-class 2. In this paper, a class of graphs of f-class 1 are obtained by a constructive proof. As a result, f-colorings of these graphs with △f（G） colors are given.展开更多
Overlapping community detection has become a very hot research topic in recent decades,and a plethora of methods have been proposed.But,a common challenge in many existing overlapping community detection approaches is...Overlapping community detection has become a very hot research topic in recent decades,and a plethora of methods have been proposed.But,a common challenge in many existing overlapping community detection approaches is that the number of communities K must be predefined manually.We propose a flexible nonparametric Bayesian generative model for count-value networks,which can allow K to increase as more and more data are encountered instead of to be fixed in advance.The Indian buffet process was used to model the community assignment matrix Z,and an uncol-lapsed Gibbs sampler has been derived.However,as the community assignment matrix Zis a structured multi-variable parameter,how to summarize the posterior inference results andestimate the inference quality about Z,is still a considerable challenge in the literature.In this paper,a graph convolutional neural network based graph classifier was utilized to help tosummarize the results and to estimate the inference qualityabout Z.We conduct extensive experiments on synthetic data and real data,and find that empirically,the traditional posterior summarization strategy is reliable.展开更多
The condition of the road infrastructure has severe impacts on the road safety, driving comfort, and on the rolling resistance. Therefore, the road infrastructure must be moni- tored comprehensively and in regular int...The condition of the road infrastructure has severe impacts on the road safety, driving comfort, and on the rolling resistance. Therefore, the road infrastructure must be moni- tored comprehensively and in regular intervals to identify damaged road segments and road hazards. Methods have been developed to comprehensively and automatically digitize the road infrastructure and estimate the road quality, which are based on vehicle sensors and a supervised machine learning classification. Since different types of vehicles have various suspension systems with different response functions, one classifier cannot be taken over to other vehicles. Usually, a high amount of time is needed to acquire training data for each individual vehicle and classifier. To address this problem, the methods to collect training data automatically for new vehicles based on the comparison of trajectories of untrained and trained vehicles have been developed. The results show that the method based on a k-dimensional tree and Euclidean distance performs best and is robust in transferring the information of the road surface from one vehicle to another. Furthermore, this method offers the possibility to merge the output and road infrastructure information from multiple vehicles to enable a more robust and precise prediction of the ground truth.展开更多
基金supported in part by National Key R&D Program of China under Grant 2023YFB3106801in part by Jiangsu Province Natural Science Foundation Project under Grant BK20231413+1 种基金in part by the National Natural Science Foundation of China under Grants 61602114 and 62172093in part by the Special Funds for Basic Scientific Research Operations of Central Universities under Grant 2242024K30021。
文摘Due to its anonymity and decentralization,Bitcoin has long been a haven for various illegal activities.Cybercriminals generally legalize illicit funds by Bitcoin mixing services.Therefore,it is critical to investigate the mixing services in cryptocurrency anti-money laundering.Existing studies treat different mixing services as a class of suspicious Bitcoin entities.Furthermore,they are limited by relying on expert experience or needing to deal with large-scale networks.So far,multi-class mixing service identification has not been explored yet.It is challenging since mixing services share a similar procedure,presenting no sharp distinctions.However,mixing service identification facilitates the healthy development of Bitcoin,supports financial forensics for cryptocurrency regulation and legislation,and provides technical means for fine-grained blockchain supervision.This paper aims to achieve multi-class Bitcoin Mixing Service Identification with a Graph Classification(BMSI-GC)model.First,BMSI-GC constructs 2-hop ego networks(2-egonets)of mixing services based on their historical transactions.Second,it applies graph2vec,a graph classification model mainly used to calculate the similarity between graphs,to automatically extract address features from the constructed 2-egonets.Finally,it trains a multilayer perceptron classifier to perform classification based on the extracted features.BMSI-GC is flexible without handling the full-size network and handcrafting address features.Moreover,the differences in transaction patterns of mixing services reflected in the 2-egonets provide adequate information for identification.Our experimental study demonstrates that BMSI-GC performs excellently in multi-class Bitcoin mixing service identification,achieving an average identification F1-score of 95.08%.
文摘Graph-based image classification has emerged as a powerful alternative to traditional convolutional approaches,leveraging the relational structure between image regions to improve accuracy.This paper presents an enhanced graph-based image classification framework that integrates convolutional neural network(CNN)features with graph convolutional network(GCN)learning,leveraging superpixel-based image representations.The proposed framework initiates the process by segmenting input images into significant superpixels,reducing computational complexity while preserving essential spatial structures.A pre-trained CNN backbone extracts both global and local features from these superpixels,capturing critical texture and shape information.These features are structured into a graph,and the framework presents a graph classification model that learns and propagates relationships between nodes,improving global contextual understanding.By combining the strengths of CNN-based feature extraction and graph-based relational learning,the method achieves higher accuracy,faster training speeds,and greater robustness in image classification tasks.Experimental evaluations on four agricultural datasets demonstrate the proposed model’s superior performance,achieving accuracy rates of 96.57%,99.63%,95.19%,and 90.00%on Tomato Leaf Disease,Dragon Fruit,Tomato Ripeness,and Dragon Fruit and Leaf datasets,respectively.The model consistently outperforms conventional CNN(89.27%–94.23%accuracy),VIT(89.45%–99.77%accuracy),VGG16(93.97%–99.52%accuracy),and ResNet50(86.67%–99.26%accuracy)methods across all datasets,with particularly significant improvements on challenging datasets such as Tomato Ripeness(95.19%vs.86.67%–94.44%)and Dragon Fruit and Leaf(90.00%vs.82.22%–83.97%).The compact superpixel representation and efficient feature propagation mechanism further accelerate learning compared to traditional CNN and graph-based approaches.
基金funded by the National Key Research and Development Program of China(Grant No.2024YFE0209000)the NSFC(Grant No.U23B2019).
文摘Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.However,despite their success,GNNs remain vulnerable to adversarial attacks that can significantly degrade their classification accuracy.Existing adversarial attack strategies primarily rely on label information to guide the attacks,which limits their applicability in scenarios where such information is scarce or unavailable.This paper introduces an innovative unsupervised attack method for graph classification,which operates without relying on label information,thereby enhancing its applicability in a broad range of scenarios.Specifically,our method first leverages a graph contrastive learning loss to learn high-quality graph embeddings by comparing different stochastic augmented views of the graphs.To effectively perturb the graphs,we then introduce an implicit estimator that measures the impact of various modifications on graph structures.The proposed strategy identifies and flips edges with the top-K highest scores,determined by the estimator,to maximize the degradation of the model’s performance.In addition,to defend against such attack,we propose a lightweight regularization-based defense mechanism that is specifically tailored to mitigate the structural perturbations introduced by our attack strategy.It enhances model robustness by enforcing embedding consistency and edge-level smoothness during training.We conduct experiments on six public TU graph classification datasets:NCI1,NCI109,Mutagenicity,ENZYMES,COLLAB,and DBLP_v1,to evaluate the effectiveness of our attack and defense strategies.Under an attack budget of 3,the maximum reduction in model accuracy reaches 6.67%on the Graph Convolutional Network(GCN)and 11.67%on the Graph Attention Network(GAT)across different datasets,indicating that our unsupervised method induces degradation comparable to state-of-the-art supervised attacks.Meanwhile,our defense achieves the highest accuracy recovery of 3.89%(GCN)and 5.00%(GAT),demonstrating improved robustness against structural perturbations.
基金National Natural Science Foundation of China(Nos.62106131,62036006,62106134 and 62276162)Fund Program for the Scientific Activities of Selected Returned Overseas Professionals in Shanxi Province,China(No.20220002)+3 种基金Research Project Supported by Shanxi Scholarship Council of China(No.2022-007)Key Research and Development Program of Shaanxi,China(No.2022ZDLGY01-13)Australian Research Council(ARC)(Nos.LP180100114 and DP200102611)Key R&D Program of Shanxi Province,China(No.202202020101003).
文摘Graph neural networks(GNNs)have achieved state-of-the-art performance on graph classification tasks,which aim to pre-dict the class labels of entire graphs and have widespread applications.However,existing GNN based methods for graph classification are data-hungry and ignore the fact that labeling graph examples is extremely expensive due to the intrinsic complexity.More import-antly,real-world graph data are often scattered in different locations.Motivated by these observations,this article presents federated collaborative graph neural networks for few-shot graph classification,termed FCGNN.With its owned graph examples,each client first trains two branches to collaboratively characterize each graph from different views and obtains a high-quality local few-shot graph learn-ing model that can generalize to novel categories not seen while training.In each branch,initial graph embeddings are extracted by any GNN and the relation information among graph examples is incorporated to produce refined graph representations via relation aggrega-tion layers for few-shot graph classification,which can reduce over-fitting while learning with scarce labeled graph examples.Finally,multiple clients owning graph data unitedly train the few-shot graph classification models with better generalization ability and effect-ively tackle the graph data island issue.Extensive experimental results on few-shot graph classification benchmarks demonstrate the ef-fectiveness and superiority of our proposed framework.
基金The research is funded by the Researchers Supporting Project at King Saud University(Project#RSP-2021/305).
文摘Graphs are used in various disciplines such as telecommunication,biological networks,as well as social networks.In large-scale networks,it is challenging to detect the communities by learning the distinct properties of the graph.As deep learning hasmade contributions in a variety of domains,we try to use deep learning techniques to mine the knowledge from large-scale graph networks.In this paper,we aim to provide a strategy for detecting communities using deep autoencoders and obtain generic neural attention to graphs.The advantages of neural attention are widely seen in the field of NLP and computer vision,which has low computational complexity for large-scale graphs.The contributions of the paper are summarized as follows.Firstly,a transformer is utilized to downsample the first-order proximities of the graph into a latent space,which can result in the structural properties and eventually assist in detecting the communities.Secondly,the fine-tuning task is conducted by tuning variant hyperparameters cautiously,which is applied to multiple social networks(Facebook and Twitch).Furthermore,the objective function(crossentropy)is tuned by L0 regularization.Lastly,the reconstructed model forms communities that present the relationship between the groups.The proposed robust model provides good generalization and is applicable to obtaining not only the community structures in social networks but also the node classification.The proposed graph-transformer shows advanced performance on the social networks with the average NMIs of 0.67±0.04,0.198±0.02,0.228±0.02,and 0.68±0.03 on Wikipedia crocodiles,Github Developers,Twitch England,and Facebook Page-Page networks,respectively.
文摘We introduce the triple crossing number, a variation of the crossing number, of a graph, which is the minimal number of crossing points in all drawings of the graph with only triple crossings. It is defined to be zero for planar graphs, and to be infinite for non-planar graphs which do not admit a drawing with only triple crossings. In this paper, we determine the triple crossing numbers for all complete multipartite graphs which include all complete graphs.
文摘Emotional electroencephalography(EEG)signals are a primary means of recording emotional brain activity.Currently,the most effective methods for analyzing emotional EEG signals involve feature engineering and neural networks.However,neural networks possess a strong ability for automatic feature extraction.Is it possible to discard feature engineering and directly employ neural networks for end-to-end recognition?Based on the characteristics of EEG signals,this paper proposes an end-to-end feature extraction and classification method for a dynamic self-attention network(DySAT).The study reveals significant differences in brain activity patterns associated with different emotions across various experimenters and time periods.The results of this experiment can provide insights into the reasons behind these differences.
基金supported by National Natural Science Foundation of China(Nos.11461017,12361068)Hainan Provincial Natural Science Foundation of China(No.125RC628)。
文摘Given a distribution of pebbles on the vertices of a connected graph G,a pebbling move on G consists of taking two pebbles off one vertex and placing one on an adjacent vertex.Rubbling is a version of pebbling where an additional move is allowed.In this new move,one pebble each is removed at vertices u and w that are adjacent to a vertex v,and an extra pebble is added at vertex v.The rubbling number of G,denoted byρ(G),is the smallest number m such that for every distribution of m pebbles on G and every vertex v,at least one pebble can be moved to v by a sequence of rubbling moves.The optimal rubbling number of G,denoted byρopt(G),is the smallest number k such that for some distribution of k pebbles on G,one pebble can be moved to any vertex of G.In this paper,we determineρ(G)for a non-complete bipartite graph G∈B(s,t)with,give an upper bound ofρ(G)for G∈B(s,t)withδ(G)≥[2s+1/3],give an upper bound ofρ(G)for G∈B(s,t),withδ(G)≥[s+1/2],and also obtainρopt(G)for a non-complete bipartite graph G∈B(s,t)withδ(G)≥[s+1/2],where B(s,t)is the set of all connected bipartite graphs with partite sets of size s and t(s≥t)andδ(G)is the minimum degree of G.
基金Supported by the National Natural Science Foun-dation of China (60403027)
文摘This paper proposes an algorithm applied in se mantic P2P network based on the description logics with the purpose for realizing the concepts distribution of resources, which makes the resources semantic locating easy. With the idea of the consistent hashing in the Chord, our algorithm stores the addresses and resources with the values of the same type to select instance. In addition, each peer has its own ontology, which will be completed by the knowledge distributed over the network during the exchange of CHGs （classification hierarchy graphs）. The hierarchy classification of concepts allows to find matching resource by querying to the upper level concept because the all concepts described in the CHG have the same root.
基金supported by the National Natural Science Foundation of China(Nos.62141608 and U19B 2038),the CAAI Huawei MindSpore Open Fund.
文摘The prediction of molecular properties is a fundamental task in the field of drug discovery.Recently,graph neural networks(GNNs)have been gaining prominence in this area.Since a molecule tends to have multiple correlated properties,there is a great need to develop the multi-task learning ability of GNNs.However,limited by expensive and time-consuming human annotations,collecting complete labels for each task is difficult.As a result,most existing benchmarks involve many missing labels in training data,and the performance of GNNs is impaired due to the lack of sufficient supervision information.To overcome this obstacle,we propose to improve multi-task molecular property prediction by missing label imputation.Specifically,a bipartite graph is first introduced to model the molecule-task co-occurrence relationships.Then,the imputation of missing labels is transformed into predicting missing edges on this bipartite graph.To predict the missing edges,a graph neural network is devised,which can learn the complex molecule-task co-occurrence relationships.After that,we select reliable pseudo labels according to the uncertainty of the prediction results.Boosting with enough and reliable supervision information,our approach achieves state-of-the-art performance on a variety of real-world datasets.
基金NSFC (10471078,60673047)RSDP (20040422004)NSF of Hebei(A2007000002) of China
文摘An f-coloring of a graph G is an edge-coloring of G such that each color appears at each vertex v V（G） at most f（v） times. The minimum number of colors needed to f-color G is called the f-chromatic index of G and is denoted by X′f（G）. Any simple graph G has the f-chromatic index equal to △f（G） or △f（G） ＋ 1, where △f（G） =max v V（G）{[d（v）/f（v）]}. If X′f（G） = △f（G）, then G is of f-class 1; otherwise G is of f-class 2. In this paper, a class of graphs of f-class 1 are obtained by a constructive proof. As a result, f-colorings of these graphs with △f（G） colors are given.
基金supported by the National Basic Research Program of China(973)(2012CB316402)The National Natural Science Foundation of China(Grant Nos.61332005,61725205)+3 种基金The Research Project of the North Minzu University(2019XYZJK02,2019xYZJK05,2017KJ24,2017KJ25,2019MS002)Ningxia first-classdisciplinc and scientific research projects(electronic science and technology,NXYLXK2017A07)NingXia Provincial Key Discipline Project-Computer ApplicationThe Provincial Natural Science Foundation ofNingXia(NZ17111,2020AAC03219).
文摘Overlapping community detection has become a very hot research topic in recent decades,and a plethora of methods have been proposed.But,a common challenge in many existing overlapping community detection approaches is that the number of communities K must be predefined manually.We propose a flexible nonparametric Bayesian generative model for count-value networks,which can allow K to increase as more and more data are encountered instead of to be fixed in advance.The Indian buffet process was used to model the community assignment matrix Z,and an uncol-lapsed Gibbs sampler has been derived.However,as the community assignment matrix Zis a structured multi-variable parameter,how to summarize the posterior inference results andestimate the inference quality about Z,is still a considerable challenge in the literature.In this paper,a graph convolutional neural network based graph classifier was utilized to help tosummarize the results and to estimate the inference qualityabout Z.We conduct extensive experiments on synthetic data and real data,and find that empirically,the traditional posterior summarization strategy is reliable.
基金project of Technical Aspects of Monitoring the Acoustic Quality of Infrastructure in Road Transport(3714541000)commissioned by the German Federal Environment Agencyfunded by the Federal Ministry for the Environment,Nature Conservation,Building and Nuclear Safety,Germany,within the Environmental Research Plan 2014.
文摘The condition of the road infrastructure has severe impacts on the road safety, driving comfort, and on the rolling resistance. Therefore, the road infrastructure must be moni- tored comprehensively and in regular intervals to identify damaged road segments and road hazards. Methods have been developed to comprehensively and automatically digitize the road infrastructure and estimate the road quality, which are based on vehicle sensors and a supervised machine learning classification. Since different types of vehicles have various suspension systems with different response functions, one classifier cannot be taken over to other vehicles. Usually, a high amount of time is needed to acquire training data for each individual vehicle and classifier. To address this problem, the methods to collect training data automatically for new vehicles based on the comparison of trajectories of untrained and trained vehicles have been developed. The results show that the method based on a k-dimensional tree and Euclidean distance performs best and is robust in transferring the information of the road surface from one vehicle to another. Furthermore, this method offers the possibility to merge the output and road infrastructure information from multiple vehicles to enable a more robust and precise prediction of the ground truth.
