Multimodal spatiotemporal data from smart city consumer electronics present critical challenges including cross-modal temporal misalignment,unreliable data quality,limited joint modeling of spatial and temporal depend...Multimodal spatiotemporal data from smart city consumer electronics present critical challenges including cross-modal temporal misalignment,unreliable data quality,limited joint modeling of spatial and temporal dependencies,and weak resilience to adversarial updates.To address these limitations,EdgeST-Fusion is introduced as a cross-modal federated graph transformer framework for context-aware smart city analytics.The architecture integrates cross-modal embedding networks for modality alignment,graph transformer encoders for spatial dependency modeling,temporal self-attention for dynamic pattern learning,and adaptive anomaly detection to ensure data quality and security during aggregation.A privacy-preserving federated learning protocol with differential privacy guarantees enables collaborative model training without centralizing sensitive data.The framework employs data-quality-aware weighted aggregation to enhance robustness against noisy and malicious client updates.Experimental evaluation on the GeoLife,PeMS-Bay,and SmartHome+datasets demonstrates that EdgeST-Fusion achieves 21.8%improvement in prediction accuracy,35.7%reduction in communication overhead,and 29.4%enhancement in security resilience compared to recent baselines.Real-world deployment across three smart city testbeds validates practical viability with 90.0%average accuracy and sub-250 ms inference latency.The proposed framework remains feasible for deployment on heterogeneous and resource-constrained consumer electronics devices whilemaintaining strong privacy guarantees and scalability for large-scale urban environments.展开更多
Industrial fault diagnosis is a critical challenge in complex systems,where sensor data is often noisy and interdependencies between components are difficult to capture.Traditional methods struggle to effectively mode...Industrial fault diagnosis is a critical challenge in complex systems,where sensor data is often noisy and interdependencies between components are difficult to capture.Traditional methods struggle to effectively model these complexities.This paper presents a novel approach by transforming fault diagnosis into a graph recognition task,using sensor data represented as graph-structured data with the k-nearest neighbors(KNN)algorithm.A Graph Transformer is applied to extract node and graph features,with a combined loss function of cross-entropy and weighted consistency loss to stabilize graph representations.Experiments on the TFF dataset show that Graph Transformer combined with consistency loss outperforms conventional methods in fault diagnosis accuracy,offering a promising solution for enhancing fault detection in industrial systems.展开更多
Computational approaches for predicting drug-target interactions(DTIs)are pivotal in advancing drug discovery.Current methodologies leveraging heterogeneous networks often fall short in fully integrating both local an...Computational approaches for predicting drug-target interactions(DTIs)are pivotal in advancing drug discovery.Current methodologies leveraging heterogeneous networks often fall short in fully integrating both local and global network information.To comprehensively consider network information,we propose DHGT-DTI,a novel deep learning-based approach for DTI prediction.Specifically,we capture the local and global structural information of the network from both neighborhood and meta-path per-spectives.In the neighborhood perspective,we employ a heterogeneous graph neural network(HGNN),which extends Graph Sample and Aggregate(GraphSAGE)to handle diverse node and edge types,effectively learning local network structures.In the meta-path perspective,we introduce a Graph Transformer with residual connections to model higher-order relationships defined by meta-paths,such as"drug-disease-drug",and use an attention mechanism to fuse information across multiple meta-paths.The learned features from these dual perspectives are synergistically integrated for DTI prediction via a matrix decomposition method.Furthermore,DHGT-DTI reconstructs not only the DTI network but also auxiliary networks to bolster prediction accuracy.Comprehensive experiments on two benchmark datasets validate the superiority of DHGT-DTI over existing baseline methods.Additionally,case studies on six drugs used to treat Parkinson's disease not only validate the practical utility of DHGT-DTI but also highlight its broader potential in accelerating drug discovery for other diseases.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
Comorbidity,the co-occurrence of multiple medical conditions in a single patient,profoundly impacts disease management and outcomes.Understanding these complex interconnections is crucial,especially in contexts where ...Comorbidity,the co-occurrence of multiple medical conditions in a single patient,profoundly impacts disease management and outcomes.Understanding these complex interconnections is crucial,especially in contexts where comorbidities exacerbate outcomes.Leveraging insights from the human interactome and advancements in graph-based methodologies,this study introduces transformer with subgraph positional encoding(TSPE)for disease comorbidity prediction.Inspired by biologically supervised embedding,TSPE employs transformer's attention mechanisms and subgraph positional encoding(SPE)to capture interactions between nodes and disease associations.Our proposed SPE proves more effective than Laplacian positional encoding,as used in Dwivedi et al.'s graph transformer,underscoring the importance of integrating clustering and disease-specific information for improved predictive accuracy.Evaluated on real clinical benchmark datasets(RR0 and RR1),TSPE demonstrates substantial performance enhancements over the state-of-the-art method,achieving up to 28.24%higher ROC AUC(receiver operating characteristic-area under the curve)and 4.93%higher accuracy.This method shows promise for adaptation to other complex graph-based tasks and applications.The source code is available at GitHub website(xihan-qin/TSPE-GraphTransformer).展开更多
In recent years,graph transformers have been demonstrated to be effective learning architectures for various graphbased learning tasks.However,their scalability on large-scale data is usually restricted due to the qua...In recent years,graph transformers have been demonstrated to be effective learning architectures for various graphbased learning tasks.However,their scalability on large-scale data is usually restricted due to the quadratic computational complexity of graph transformers when compared to graph convolutional network(GCN)models.To overcome this issue,in this work,we propose to learn an efficient linear graph transformer by employing graph attention distillation model.The proposed method provides a faster and lighter graph transformer framework for graph data learning tasks.The core of the proposed distillation model is to employ the kernel decomposition approach to rebuild the graph transformer architecture,thereby reducing the quadratic complexity to the linear complexity.Furthermore,to seamlessly transfer the rich learning capacity from the regular graph transformer of teacher branch to its linear student counterpart,we devise a novel graph-attention knowledge distillation strategy to enhance the capabilities of the student network.Empirical evaluations conducted on six commonly employed benchmark datasets validate our model′s superiority,as it consistently outperforms existing methods in terms of both effectiveness and efficiency.展开更多
Low-Earth orbit( LEO) satellite networks are a critical architectural evolution in transitioning from the 5 th generation( 5G) to the 6 th generation( 6G). It is imperative to address the challenges of efficient routi...Low-Earth orbit( LEO) satellite networks are a critical architectural evolution in transitioning from the 5 th generation( 5G) to the 6 th generation( 6G). It is imperative to address the challenges of efficient routing and data transmission within these networks. A novel GTE-ACO routing algorithm was proposed in this paper which combines graph transformer enhancements with ant colony optimization( ACO) based on the principles of swarm intelligence.A specialized method for representing LEO satellite networks using graph transformers is introduced. Initial heuristic outputs for the ACO are provided via neural network representations. An efficient reinforcement training approach is combined with unsupervised training of a routing algorithm using probability sampling techniques. The simulation results demonstrate the good convergence of the training and the significantly superior performance of the GTE-ACO compared to traditional routing algorithms in terms of cost function minimization and routing success rates. The routing cost can be reduced by 51. 3% compared to baseline algorithms.展开更多
Thetransformer-based semantic segmentation approaches,which divide the image into different regions by sliding windows and model the relation inside each window,have achieved outstanding success.However,since the rela...Thetransformer-based semantic segmentation approaches,which divide the image into different regions by sliding windows and model the relation inside each window,have achieved outstanding success.However,since the relation modeling between windows was not the primary emphasis of previous work,it was not fully utilized.To address this issue,we propose a Graph-Segmenter,including a graph transformer and a boundary-aware attention module,which is an effective network for simultaneously modeling the more profound relation between windows in a global view and various pixels inside each window as a local one,and for substantial low-cost boundary adjustment.Specifically,we treat every window and pixel inside the window as nodes to construct graphs for both views and devise the graph transformer.The introduced boundary-awareattentionmoduleoptimizes theedge information of the target objects by modeling the relationship between the pixel on the object's edge.Extensive experiments on three widely used semantic segmentation datasets(Cityscapes,ADE-20k and PASCAL Context)demonstrate that our proposed network,a Graph Transformer with Boundary-aware Attention,can achieve state-of-the-art segmentation performance.展开更多
The basis graph \%G\% for a linear programming consists of all bases under pivot transformations. A degenerate optimal basis graph G * is a subgraph of \%G\% induced by all optimal bases at a degenerate optimal verte...The basis graph \%G\% for a linear programming consists of all bases under pivot transformations. A degenerate optimal basis graph G * is a subgraph of \%G\% induced by all optimal bases at a degenerate optimal vertex x 0. In this paper, several conditions for the characterization of G * are presented.展开更多
Graph transformation systems have become a general formal modeling language to describe many models in software development process.Behavioral modeling of dynamic systems and model-to-model transformations are only a ...Graph transformation systems have become a general formal modeling language to describe many models in software development process.Behavioral modeling of dynamic systems and model-to-model transformations are only a few examples in which graphs have been used to software development.But even the perfect graph transformation system must be equipped with automated analysis capabilities to let users understand whether such a formal specification fulfills their requirements.In this paper,we present a new solution to verify graph transformation systems using the Bogor model checker.The attributed graph grammars(AGG)-like graph transformation systems are translated to Bandera intermediate representation(BIR),the input language of Bogor,and Bogor verifies the model against some interesting properties defined by combining linear temporal logic(LTL) and special-purpose graph rules.Experimental results are encouraging,showing that in most cases our solution improves existing approaches in terms of both performance and expressiveness.展开更多
The properties of generalized flip Markov chains on connected regular digraphs are discussed.The 1-Flipper operation on Markov chains for undirected graphs is generalized to that for multi-digraphs.The generalized 1-F...The properties of generalized flip Markov chains on connected regular digraphs are discussed.The 1-Flipper operation on Markov chains for undirected graphs is generalized to that for multi-digraphs.The generalized 1-Flipper operation preserves the regularity and weak connectivity of multi-digraphs.The generalized 1-Flipper operation is proved to be symmetric.Moreover,it is presented that a series of random generalized 1-Flipper operations eventually lead to a uniform probability distribution over all connected d-regular multi-digraphs without loops.展开更多
Circuits with switched current are described by an admittance matrix and seeking current transfers then means calculating the ratio of algebraic supplements of this matrix. As there are also graph methods of circuit a...Circuits with switched current are described by an admittance matrix and seeking current transfers then means calculating the ratio of algebraic supplements of this matrix. As there are also graph methods of circuit analysis in addition to algebraic methods, it is clearly possible in theory to carry out an analysis of the whole switched circuit in two-phase switching exclusively by the graph method as well. For this purpose it is possible to plot a Mason graph of a circuit, use transformation graphs to reduce Mason graphs for all the four phases of switching, and then plot a summary graph from the transformed graphs obtained this way. First the author draws nodes and possible branches, obtained by transformation graphs for transfers of EE （even-even） and OO （odd-odd） phases. In the next step, branches obtained by transformation graphs for EO and OE phase are drawn between these nodes, while their resulting transfer is 1 multiplied by z^1/2. This summary graph is extended by two branches from input node and to output node, the extended graph can then be interpreted by the Mason＇s relation to provide transparent current transfers. Therefore it is not necessary to compose a sum admittance matrix and to express this consequently in numbers, and so it is possible to reach the final result in a graphical way.展开更多
基金supported by the University of Tabuk,Saudi Arabia。
文摘Multimodal spatiotemporal data from smart city consumer electronics present critical challenges including cross-modal temporal misalignment,unreliable data quality,limited joint modeling of spatial and temporal dependencies,and weak resilience to adversarial updates.To address these limitations,EdgeST-Fusion is introduced as a cross-modal federated graph transformer framework for context-aware smart city analytics.The architecture integrates cross-modal embedding networks for modality alignment,graph transformer encoders for spatial dependency modeling,temporal self-attention for dynamic pattern learning,and adaptive anomaly detection to ensure data quality and security during aggregation.A privacy-preserving federated learning protocol with differential privacy guarantees enables collaborative model training without centralizing sensitive data.The framework employs data-quality-aware weighted aggregation to enhance robustness against noisy and malicious client updates.Experimental evaluation on the GeoLife,PeMS-Bay,and SmartHome+datasets demonstrates that EdgeST-Fusion achieves 21.8%improvement in prediction accuracy,35.7%reduction in communication overhead,and 29.4%enhancement in security resilience compared to recent baselines.Real-world deployment across three smart city testbeds validates practical viability with 90.0%average accuracy and sub-250 ms inference latency.The proposed framework remains feasible for deployment on heterogeneous and resource-constrained consumer electronics devices whilemaintaining strong privacy guarantees and scalability for large-scale urban environments.
基金supported by the National Natural Science Foundation of China under Grants Nos.62573292,62206199 and 62476192National Key Laboratory of Marine Engine Science and Technology under Grant No.LAB-2024-04-WD+2 种基金Young Elite Scientist Sponsorship Program under Grant No.YESS20220409the Hainan Province Science and Technology Special Fund under Grant No.ZDYF2024GXJS003the Natural Science Foundation of Tianjin under Grant No.23JCQNJC02010.
文摘Industrial fault diagnosis is a critical challenge in complex systems,where sensor data is often noisy and interdependencies between components are difficult to capture.Traditional methods struggle to effectively model these complexities.This paper presents a novel approach by transforming fault diagnosis into a graph recognition task,using sensor data represented as graph-structured data with the k-nearest neighbors(KNN)algorithm.A Graph Transformer is applied to extract node and graph features,with a combined loss function of cross-entropy and weighted consistency loss to stabilize graph representations.Experiments on the TFF dataset show that Graph Transformer combined with consistency loss outperforms conventional methods in fault diagnosis accuracy,offering a promising solution for enhancing fault detection in industrial systems.
基金the National Natural Science Foundation of China(Grant Nos.:62272288,U22A2041)Fundamental Research Funds for the Central Universities,Shaanxi Normal University(Grant No.:GK202302006)the Scientific Research Fund of Hunan Provincial Education Department of China(Grant No.:22B0097).
文摘Computational approaches for predicting drug-target interactions(DTIs)are pivotal in advancing drug discovery.Current methodologies leveraging heterogeneous networks often fall short in fully integrating both local and global network information.To comprehensively consider network information,we propose DHGT-DTI,a novel deep learning-based approach for DTI prediction.Specifically,we capture the local and global structural information of the network from both neighborhood and meta-path per-spectives.In the neighborhood perspective,we employ a heterogeneous graph neural network(HGNN),which extends Graph Sample and Aggregate(GraphSAGE)to handle diverse node and edge types,effectively learning local network structures.In the meta-path perspective,we introduce a Graph Transformer with residual connections to model higher-order relationships defined by meta-paths,such as"drug-disease-drug",and use an attention mechanism to fuse information across multiple meta-paths.The learned features from these dual perspectives are synergistically integrated for DTI prediction via a matrix decomposition method.Furthermore,DHGT-DTI reconstructs not only the DTI network but also auxiliary networks to bolster prediction accuracy.Comprehensive experiments on two benchmark datasets validate the superiority of DHGT-DTI over existing baseline methods.Additionally,case studies on six drugs used to treat Parkinson's disease not only validate the practical utility of DHGT-DTI but also highlight its broader potential in accelerating drug discovery for other diseases.
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Comorbidity,the co-occurrence of multiple medical conditions in a single patient,profoundly impacts disease management and outcomes.Understanding these complex interconnections is crucial,especially in contexts where comorbidities exacerbate outcomes.Leveraging insights from the human interactome and advancements in graph-based methodologies,this study introduces transformer with subgraph positional encoding(TSPE)for disease comorbidity prediction.Inspired by biologically supervised embedding,TSPE employs transformer's attention mechanisms and subgraph positional encoding(SPE)to capture interactions between nodes and disease associations.Our proposed SPE proves more effective than Laplacian positional encoding,as used in Dwivedi et al.'s graph transformer,underscoring the importance of integrating clustering and disease-specific information for improved predictive accuracy.Evaluated on real clinical benchmark datasets(RR0 and RR1),TSPE demonstrates substantial performance enhancements over the state-of-the-art method,achieving up to 28.24%higher ROC AUC(receiver operating characteristic-area under the curve)and 4.93%higher accuracy.This method shows promise for adaptation to other complex graph-based tasks and applications.The source code is available at GitHub website(xihan-qin/TSPE-GraphTransformer).
基金supported by National Natural Science Foundation of China(No.62076004)Anhui Provincial Key Research and Development Program,China(No.2022i01020014).
文摘In recent years,graph transformers have been demonstrated to be effective learning architectures for various graphbased learning tasks.However,their scalability on large-scale data is usually restricted due to the quadratic computational complexity of graph transformers when compared to graph convolutional network(GCN)models.To overcome this issue,in this work,we propose to learn an efficient linear graph transformer by employing graph attention distillation model.The proposed method provides a faster and lighter graph transformer framework for graph data learning tasks.The core of the proposed distillation model is to employ the kernel decomposition approach to rebuild the graph transformer architecture,thereby reducing the quadratic complexity to the linear complexity.Furthermore,to seamlessly transfer the rich learning capacity from the regular graph transformer of teacher branch to its linear student counterpart,we devise a novel graph-attention knowledge distillation strategy to enhance the capabilities of the student network.Empirical evaluations conducted on six commonly employed benchmark datasets validate our model′s superiority,as it consistently outperforms existing methods in terms of both effectiveness and efficiency.
基金supported by the National Key Research and Development Program of China (2020YFB1808000)。
文摘Low-Earth orbit( LEO) satellite networks are a critical architectural evolution in transitioning from the 5 th generation( 5G) to the 6 th generation( 6G). It is imperative to address the challenges of efficient routing and data transmission within these networks. A novel GTE-ACO routing algorithm was proposed in this paper which combines graph transformer enhancements with ant colony optimization( ACO) based on the principles of swarm intelligence.A specialized method for representing LEO satellite networks using graph transformers is introduced. Initial heuristic outputs for the ACO are provided via neural network representations. An efficient reinforcement training approach is combined with unsupervised training of a routing algorithm using probability sampling techniques. The simulation results demonstrate the good convergence of the training and the significantly superior performance of the GTE-ACO compared to traditional routing algorithms in terms of cost function minimization and routing success rates. The routing cost can be reduced by 51. 3% compared to baseline algorithms.
文摘Thetransformer-based semantic segmentation approaches,which divide the image into different regions by sliding windows and model the relation inside each window,have achieved outstanding success.However,since the relation modeling between windows was not the primary emphasis of previous work,it was not fully utilized.To address this issue,we propose a Graph-Segmenter,including a graph transformer and a boundary-aware attention module,which is an effective network for simultaneously modeling the more profound relation between windows in a global view and various pixels inside each window as a local one,and for substantial low-cost boundary adjustment.Specifically,we treat every window and pixel inside the window as nodes to construct graphs for both views and devise the graph transformer.The introduced boundary-awareattentionmoduleoptimizes theedge information of the target objects by modeling the relationship between the pixel on the object's edge.Extensive experiments on three widely used semantic segmentation datasets(Cityscapes,ADE-20k and PASCAL Context)demonstrate that our proposed network,a Graph Transformer with Boundary-aware Attention,can achieve state-of-the-art segmentation performance.
基金Project supported by the National Natural Science Foundation of China!(19771075)
文摘The basis graph \%G\% for a linear programming consists of all bases under pivot transformations. A degenerate optimal basis graph G * is a subgraph of \%G\% induced by all optimal bases at a degenerate optimal vertex x 0. In this paper, several conditions for the characterization of G * are presented.
文摘Graph transformation systems have become a general formal modeling language to describe many models in software development process.Behavioral modeling of dynamic systems and model-to-model transformations are only a few examples in which graphs have been used to software development.But even the perfect graph transformation system must be equipped with automated analysis capabilities to let users understand whether such a formal specification fulfills their requirements.In this paper,we present a new solution to verify graph transformation systems using the Bogor model checker.The attributed graph grammars(AGG)-like graph transformation systems are translated to Bandera intermediate representation(BIR),the input language of Bogor,and Bogor verifies the model against some interesting properties defined by combining linear temporal logic(LTL) and special-purpose graph rules.Experimental results are encouraging,showing that in most cases our solution improves existing approaches in terms of both performance and expressiveness.
基金National Natural Science Foundation of China(No.11671258)。
文摘The properties of generalized flip Markov chains on connected regular digraphs are discussed.The 1-Flipper operation on Markov chains for undirected graphs is generalized to that for multi-digraphs.The generalized 1-Flipper operation preserves the regularity and weak connectivity of multi-digraphs.The generalized 1-Flipper operation is proved to be symmetric.Moreover,it is presented that a series of random generalized 1-Flipper operations eventually lead to a uniform probability distribution over all connected d-regular multi-digraphs without loops.
文摘Circuits with switched current are described by an admittance matrix and seeking current transfers then means calculating the ratio of algebraic supplements of this matrix. As there are also graph methods of circuit analysis in addition to algebraic methods, it is clearly possible in theory to carry out an analysis of the whole switched circuit in two-phase switching exclusively by the graph method as well. For this purpose it is possible to plot a Mason graph of a circuit, use transformation graphs to reduce Mason graphs for all the four phases of switching, and then plot a summary graph from the transformed graphs obtained this way. First the author draws nodes and possible branches, obtained by transformation graphs for transfers of EE （even-even） and OO （odd-odd） phases. In the next step, branches obtained by transformation graphs for EO and OE phase are drawn between these nodes, while their resulting transfer is 1 multiplied by z^1/2. This summary graph is extended by two branches from input node and to output node, the extended graph can then be interpreted by the Mason＇s relation to provide transparent current transfers. Therefore it is not necessary to compose a sum admittance matrix and to express this consequently in numbers, and so it is possible to reach the final result in a graphical way.
