Smart contracts have led to more efficient development in finance and healthcare,but vulnerabilities in contracts pose high risks to their future applications.The current vulnerability detection methods for contracts ...Smart contracts have led to more efficient development in finance and healthcare,but vulnerabilities in contracts pose high risks to their future applications.The current vulnerability detection methods for contracts are either based on fixed expert rules,which are inefficient,or rely on simplistic deep learning techniques that do not fully leverage contract semantic information.Therefore,there is ample room for improvement in terms of detection precision.To solve these problems,this paper proposes a vulnerability detector based on deep learning techniques,graph representation,and Transformer,called GRATDet.The method first performs swapping,insertion,and symbolization operations for contract functions,increasing the amount of small sample data.Each line of code is then treated as a basic semantic element,and information such as control and data relationships is extracted to construct a new representation in the form of a Line Graph(LG),which shows more structural features that differ from the serialized presentation of the contract.Finally,the node information and edge information of the graph are jointly learned using an improved Transformer-GP model to extract information globally and locally,and the fused features are used for vulnerability detection.The effectiveness of the method in reentrancy vulnerability detection is verified in experiments,where the F1 score reaches 95.16%,exceeding stateof-the-art methods.展开更多
Graph representation learning often faces knowledge scarcity in real-world applications,including limited labels and sparse relationships.Although a range of methods have been proposed to address these problems,such a...Graph representation learning often faces knowledge scarcity in real-world applications,including limited labels and sparse relationships.Although a range of methods have been proposed to address these problems,such as graph few-shot learning,they mainly rely on inadequate knowledge within the task graph,which would limit their effectiveness.Moreover,they fail to consider other potentially useful task-related graphs.To overcome these limitations,domain adaptation for graph representation learning has emerged as an effective paradigm for transferring knowledge across graphs.It is also recognized as graph domain adaptation(GDA).In particular,to enhance model performance on target graphs with specific tasks,GDA introduces a bunch of task-related graphs as source graphs and adapts the knowledge learnt from source graphs to the target graphs.Since GDA combines the advantages of graph representation learning and domain adaptation,it has become a promising direction of transfer learning on graphs and has attracted an increasing amount of research interest in recent years.In this paper,we comprehensively overview the studies of GDA and present a detailed survey of recent advances.Specifically,we outline the current research status,analyze key challenges,propose a taxonomy,introduce representative work and practical applications,and discuss future prospects.To the best of our knowledge,this paper is the first survey for graph domain adaptation.展开更多
Various graph representation learning models convert graph nodes into vectors using techniques like matrix factorization,random walk,and deep learning.However,choosing the right method for different tasks can be chall...Various graph representation learning models convert graph nodes into vectors using techniques like matrix factorization,random walk,and deep learning.However,choosing the right method for different tasks can be challenging.Communities within networks help reveal underlying structures and correlations.Investigating how different models preserve community properties is crucial for identifying the best graph representation for data analysis.This paper defines indicators to explore the perceptual quality of community properties in representation learning spaces,including the consistency of community structure,node distribution within and between communities,and central node distribution.A visualization system presents these indicators,allowing users to evaluate models based on community structures.Case studies demonstrate the effectiveness of the indicators for the visual evaluation of graph representation learning models.展开更多
The escalating complexity and heterogeneity of modern energy systems—particularly in smart grid and distributed energy infrastructures—has intensified the need for intelligent and scalable security vulnerability cla...The escalating complexity and heterogeneity of modern energy systems—particularly in smart grid and distributed energy infrastructures—has intensified the need for intelligent and scalable security vulnerability classification.To address this challenge,we propose Vulnerability2Vec,a graph-embedding-based framework designed to enhance the automated classification of security vulnerabilities that threaten energy system resilience.Vulnerability2Vec converts Common Vulnerabilities and Exposures(CVE)text explanations to semantic graphs,where nodes represent CVE IDs and key terms(nouns,verbs,and adjectives),and edges capture co-occurrence relationships.Then,it embeds the semantic graphs to a low-dimensional vector space with random-walk sampling and skip-gram with negative sampling.It is possible to identify the latent relationships and structural patterns that traditional sparse vector methods fail to capture.Experimental results demonstrate a classification accuracy of up to 80%,significantly outperforming baseline methods.This approach offers a theoretical basis for classifying vulnerability types as structured semantic patterns in complex software systems.The proposed method models the semantic structure of vulnerabilities,providing a theoretical foundation for their classification.展开更多
The proliferation of internet traffic encryption has become a double-edged sword. While it significantly enhances user privacy, it also inadvertently shields cyber-attacks from detection, presenting a formidable chall...The proliferation of internet traffic encryption has become a double-edged sword. While it significantly enhances user privacy, it also inadvertently shields cyber-attacks from detection, presenting a formidable challenge to cybersecurity. Traditional machine learning and deep learning techniques often fall short in identifying encrypted malicious traffic due to their inability to fully extract and utilize the implicit relational and positional information embedded within data packets. This limitation has led to an unresolved challenge in the cybersecurity community: how to effectively extract valuable insights from the complex patterns of traffic packet transmission. Consequently, this paper introduces the TB-Graph model, an encrypted malicious traffic classification model based on a relational graph attention network. The model is a heterogeneous traffic burst graph that embeds side-channel features, which are unaffected by encryption, into the graph nodes and connects them with three different types of burst edges. Subsequently, we design a relational positional coding that prevents the loss of temporal relationships between the original traffic flows during graph transformation. Ultimately, TB-Graph leverages the powerful graph representation learning capabilities of Relational Graph Attention Network (RGAT) to extract latent behavioral features from the burst graph nodes and edge relationships. Experimental results show that TB-Graph outperforms various state-of-the-art methods in fine-grained encrypted malicious traffic classification tasks on two public datasets, indicating its enhanced capability for identifying encrypted malicious traffic.展开更多
The performance of proton exchange membrane fuel cells depends heavily on the oxygen reduction reaction(ORR)at the cathode,for which platinum-based catalysts are currently the standard.The high cost and limited availa...The performance of proton exchange membrane fuel cells depends heavily on the oxygen reduction reaction(ORR)at the cathode,for which platinum-based catalysts are currently the standard.The high cost and limited availability of platinum have driven the search for alternative catalysts.While FeN4 single-atom catalysts have shown promising potential,their ORR activity needs to be further enhanced.In contrast,dual-atom catalysts(DACs)offer not only higher metal loading but also the ability to break the ORR scaling relations.However,the diverse local structures and tunable coordination environments of DACs create a vast chemical space,making large-scale computational screening challenging.In this study,we developed a graph neural network(GNN)-based framework to predict the ORR activity of Fe-based DACs,effectively addressing the challenges posed by variations in local catalyst structures.Our model,trained on a dataset of 180 catalysts,accurately predicted the Gibbs free energy of ORR intermediates and overpotentials,and identified 32 DACs with superior catalytic activity compared to FeN4 SAC.This approach not only advances the design of high-performance DACs,but also offers a powerful computational tool that can significantly reduce the time and cost of catalyst development,thereby accelerating the commercialization of fuel cell technologies.展开更多
Unsupervised learning methods such as graph contrastive learning have been used for dynamic graph represen-tation learning to eliminate the dependence of labels.However,existing studies neglect positional information ...Unsupervised learning methods such as graph contrastive learning have been used for dynamic graph represen-tation learning to eliminate the dependence of labels.However,existing studies neglect positional information when learning discrete snapshots,resulting in insufficient network topology learning.At the same time,due to the lack of appropriate data augmentation methods,it is difficult to capture the evolving patterns of the network effectively.To address the above problems,a position-aware and subgraph enhanced dynamic graph contrastive learning method is proposed for discrete-time dynamic graphs.Firstly,the global snapshot is built based on the historical snapshots to express the stable pattern of the dynamic graph,and the random walk is used to obtain the position representation by learning the positional information of the nodes.Secondly,a new data augmentation method is carried out from the perspectives of short-term changes and long-term stable structures of dynamic graphs.Specifically,subgraph sampling based on snapshots and global snapshots is used to obtain two structural augmentation views,and node structures and evolving patterns are learned by combining graph neural network,gated recurrent unit,and attention mechanism.Finally,the quality of node representation is improved by combining the contrastive learning between different structural augmentation views and between the two representations of structure and position.Experimental results on four real datasets show that the performance of the proposed method is better than the existing unsupervised methods,and it is more competitive than the supervised learning method under a semi-supervised setting.展开更多
With the rapid advancement of 5G technology,the Internet of Things(IoT)has entered a new phase of appli-cations and is rapidly becoming a significant force in promoting economic development.Due to the vast amounts of ...With the rapid advancement of 5G technology,the Internet of Things(IoT)has entered a new phase of appli-cations and is rapidly becoming a significant force in promoting economic development.Due to the vast amounts of data created by numerous 5G IoT devices,the Ethereum platform has become a tool for the storage and sharing of IoT device data,thanks to its open and tamper-resistant characteristics.So,Ethereum account security is necessary for the Internet of Things to grow quickly and improve people's lives.By modeling Ethereum trans-action records as a transaction network,the account types are well identified by the Ethereum account classifi-cation system established based on Graph Neural Networks(GNNs).This work first investigates the Ethereum transaction network.Surprisingly,experimental metrics reveal that the Ethereum transaction network is neither optimal nor even satisfactory in terms of accurately representing transactions per account.This flaw may significantly impede the classification capability of GNNs,which is mostly governed by their attributes.This work proposes an Adaptive Multi-channel Bayesian Graph Attention Network(AMBGAT)for Ethereum account clas-sification to address this difficulty.AMBGAT uses attention to enhance node features,estimate graph topology that conforms to the ground truth,and efficiently extract node features pertinent to downstream tasks.An extensive experiment with actual Ethereum transaction data demonstrates that AMBGAT obtains competitive performance in the classification of Ethereum accounts while accurately estimating the graph topology.展开更多
Graph Neural Networks(GNNs)play a significant role in tasks related to homophilic graphs.Traditional GNNs,based on the assumption of homophily,employ low-pass filters for neighboring nodes to achieve information aggre...Graph Neural Networks(GNNs)play a significant role in tasks related to homophilic graphs.Traditional GNNs,based on the assumption of homophily,employ low-pass filters for neighboring nodes to achieve information aggregation and embedding.However,in heterophilic graphs,nodes from different categories often establish connections,while nodes of the same category are located further apart in the graph topology.This characteristic poses challenges to traditional GNNs,leading to issues of“distant node modeling deficiency”and“failure of the homophily assumption”.In response,this paper introduces the Spatial-Frequency domain Adaptive Heterophilic Graph Neural Networks(SFA-HGNN),which integrates adaptive embedding mechanisms for both spatial and frequency domains to address the aforementioned issues.Specifically,for the first problem,we propose the“Distant Spatial Embedding Module”,aiming to select and aggregate distant nodes through high-order randomwalk transition probabilities to enhance modeling capabilities.For the second issue,we design the“Proximal Frequency Domain Embedding Module”,constructing adaptive filters to separate high and low-frequency signals of nodes,and introduce frequency-domain guided attention mechanisms to fuse the relevant information,thereby reducing the noise introduced by the failure of the homophily assumption.We deploy the SFA-HGNN on six publicly available heterophilic networks,achieving state-of-the-art results in four of them.Furthermore,we elaborate on the hyperparameter selection mechanism and validate the performance of each module through experimentation,demonstrating a positive correlation between“node structural similarity”,“node attribute vector similarity”,and“node homophily”in heterophilic networks.展开更多
Objective To construct symptom-formula-herb heterogeneous graphs structured Treatise on Febrile Diseases(Shang Han Lun,《伤寒论》)dataset and explore an optimal learning method represented with node attributes based o...Objective To construct symptom-formula-herb heterogeneous graphs structured Treatise on Febrile Diseases(Shang Han Lun,《伤寒论》)dataset and explore an optimal learning method represented with node attributes based on graph convolutional network(GCN).Methods Clauses that contain symptoms,formulas,and herbs were abstracted from Treatise on Febrile Diseases to construct symptom-formula-herb heterogeneous graphs,which were used to propose a node representation learning method based on GCN−the Traditional Chinese Medicine Graph Convolution Network(TCM-GCN).The symptom-formula,symptom-herb,and formula-herb heterogeneous graphs were processed with the TCM-GCN to realize high-order propagating message passing and neighbor aggregation to obtain new node representation attributes,and thus acquiring the nodes’sum-aggregations of symptoms,formulas,and herbs to lay a foundation for the downstream tasks of the prediction models.Results Comparisons among the node representations with multi-hot encoding,non-fusion encoding,and fusion encoding showed that the Precision@10,Recall@10,and F1-score@10 of the fusion encoding were 9.77%,6.65%,and 8.30%,respectively,higher than those of the non-fusion encoding in the prediction studies of the model.Conclusion Node representations by fusion encoding achieved comparatively ideal results,indicating the TCM-GCN is effective in realizing node-level representations of heterogeneous graph structured Treatise on Febrile Diseases dataset and is able to elevate the performance of the downstream tasks of the diagnosis model.展开更多
Accurate prediction of future events brings great benefits and reduces losses for society in many domains,such as civil unrest,pandemics,and crimes.Knowledge graph is a general language for describing and modeling com...Accurate prediction of future events brings great benefits and reduces losses for society in many domains,such as civil unrest,pandemics,and crimes.Knowledge graph is a general language for describing and modeling complex systems.Different types of events continually occur,which are often related to historical and concurrent events.In this paper,we formalize the future event prediction as a temporal knowledge graph reasoning problem.Most existing studies either conduct reasoning on static knowledge graphs or assume knowledges graphs of all timestamps are available during the training process.As a result,they cannot effectively reason over temporal knowledge graphs and predict events happening in the future.To address this problem,some recent works learn to infer future events based on historical eventbased temporal knowledge graphs.However,these methods do not comprehensively consider the latent patterns and influences behind historical events and concurrent events simultaneously.This paper proposes a new graph representation learning model,namely Recurrent Event Graph ATtention Network(RE-GAT),based on a novel historical and concurrent events attention-aware mechanism by modeling the event knowledge graph sequence recurrently.More specifically,our RE-GAT uses an attention-based historical events embedding module to encode past events,and employs an attention-based concurrent events embedding module to model the associations of events at the same timestamp.A translation-based decoder module and a learning objective are developed to optimize the embeddings of entities and relations.We evaluate our proposed method on four benchmark datasets.Extensive experimental results demonstrate the superiority of our RE-GAT model comparing to various base-lines,which proves that our method can more accurately predict what events are going to happen.展开更多
Shortest-path calculation on weighted graphs are an essential operation in computer networks. The performance of such algorithms has become a critical challenge in emerging software-defined networks(SDN),since SDN con...Shortest-path calculation on weighted graphs are an essential operation in computer networks. The performance of such algorithms has become a critical challenge in emerging software-defined networks(SDN),since SDN controllers need to centralizedly perform a shortest-path query for every flow,usually on large-scale network. Unfortunately,one of the challenges is that current algorithms will become incalculable as the network size increases. Therefore, inspired by the compression graph in the field of compute visualization,we propose an efficient shortest path algorithm by compressing the original big network graph into a small one, but the important graph properties used to calculate path is reserved. We implement a centralized version of our approach in SDN-enabled network,and the evaluations validate the improvement compared with the well-known algorithms.展开更多
Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently.However,there are still two challenges.First,most of t...Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently.However,there are still two challenges.First,most of the real‐word system are multiple relations,where entities are linked by different types of relations,and each relation is a view of the graph network.Second,the rich multi‐scale information(structure‐level and feature‐level)of the graph network can be seen as self‐supervised signals,which are not fully exploited.A novel contrastive self‐supervised representation learning framework on attributed multiplex graph networks with multi‐scale(named CoLM^(2)S)information is presented in this study.It mainly contains two components:intra‐relation contrast learning and interrelation contrastive learning.Specifically,the contrastive self‐supervised representation learning framework on attributed single‐layer graph networks with multi‐scale information(CoLMS)framework with the graph convolutional network as encoder to capture the intra‐relation information with multi‐scale structure‐level and feature‐level selfsupervised signals is introduced first.The structure‐level information includes the edge structure and sub‐graph structure,and the feature‐level information represents the output of different graph convolutional layer.Second,according to the consensus assumption among inter‐relations,the CoLM^(2)S framework is proposed to jointly learn various graph relations in attributed multiplex graph network to achieve global consensus node embedding.The proposed method can fully distil the graph information.Extensive experiments on unsupervised node clustering and graph visualisation tasks demonstrate the effectiveness of our methods,and it outperforms existing competitive baselines.展开更多
Advanced Persistent Threats (APTs) achieves internal networks penetration through multiple methods, making it difcult to detect attack clues solely through boundary defense measures. To address this challenge, some re...Advanced Persistent Threats (APTs) achieves internal networks penetration through multiple methods, making it difcult to detect attack clues solely through boundary defense measures. To address this challenge, some research has proposed threat detection methods based on provenance graphs, which leverage entity relationships such as processes, fles, and sockets found in host audit logs. However, these methods are generally inefcient, especially when faced with massive audit logs and the computational resource-intensive nature of graph algorithms. Efec-tivelyand economically extracting APT attack clues from massive system audit logs remains a signifcant challenge. To tackle this problem, this paper introduces the ProcSAGE method, which detects threats based on abnormal behavior patterns, ofering high accuracy, low cost, and independence from expert knowledge. ProcSAGE focuses on processes or threads in host audit logs during the graph construction phase to efectively control the scale of provenance graphs and reduce performance overhead. Additionally, in the feature extraction phase, ProcSAGE considers information about the processes or threads themselves and their neighboring nodes to accurately char-acterizethem and enhance model accuracy. In order to verify the efectiveness of the ProcSAGE method, this study conducted a comprehensive evaluation on the StreamSpot dataset. The experimental results show that the ProcSAGE method can signifcantly reduce the time and memory consumption in the threat detection process while improving the accuracy, and the optimization efect becomes more signifcant as the data size expands.展开更多
The outbreak and subsequent recurring waves of COVID−19 pose threats on the emergency management and people's daily life,while the large-scale spatio-temporal epidemiological data have sure come in handy in epidem...The outbreak and subsequent recurring waves of COVID−19 pose threats on the emergency management and people's daily life,while the large-scale spatio-temporal epidemiological data have sure come in handy in epidemic surveillance.Nonetheless,some challenges remain to be addressed in terms of multi-source heterogeneous data fusion,deep mining,and comprehensive applications.The Spatio-Temporal Artificial Intelligence(STAI)technology,which focuses on integrating spatial related time-series data,artificial intelligence models,and digital tools to provide intelligent computing platforms and applications,opens up new opportunities for scientific epidemic control.To this end,we leverage STAI and long-term experience in location-based intelligent services in the work.Specifically,we devise and develop a STAI-driven digital infrastructure,namely,WAYZ Disease Control Intelligent Platform(WDCIP),which consists of a systematic framework for building pipelines from automatic spatio-temporal data collection,processing to AI-based analysis and inference implementation for providing appropriate applications serving various epidemic scenarios.According to the platform implementation logic,our work can be performed and summarized from three aspects:(1)a STAI-driven integrated system;(2)a hybrid GNN-based approach for hierarchical risk assessment(as the core algorithm of WDCIP);and(3)comprehensive applications for social epidemic containment.This work makes a pivotal contribution to facilitating the aggregation and full utilization of spatio-temporal epidemic data from multiple sources,where the real-time human mobility data generated by high-precision mobile positioning plays a vital role in sensing the spread of the epidemic.So far,WDCIP has accumulated more than 200 million users who have been served in life convenience and decision-making during the pandemic.展开更多
Identifying personalities accurately helps merchants and management departments understand user needs in detail and improve the quality of service and decision-making efficiency.Existing research on text-based persona...Identifying personalities accurately helps merchants and management departments understand user needs in detail and improve the quality of service and decision-making efficiency.Existing research on text-based personality prediction mainly uses deep neural networks or pretrained language models to mine deep semantics,ignoring the dynamic interactions among personality features.This paper presents a novel personality prediction method that simultaneously taps into the capability of graph neural networks to model the deep interactions among features and that of pretrained language models to learn latent semantics with a hierarchical aggregation mechanism.Specifically,the proposed model leverages self-attention to capture the interaction relationships among POS tags,entities,personality tags,etc.,and considers the labels’cooccurrence patterns.The efficacy of the proposed model is evaluated on the myPersonality and PANDORA datasets.This research contributes to the personality prediction literature from the perspective of a multigranular personality feature learning perspective and provides business value for consuming predictive analytics.展开更多
Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and ...Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and severe class imbalance,and occasional imaging artifacts can create ambiguity for state-of-the-art convolutional neural networks(CNNs).We frame skin lesion recognition as graph-based reasoning and,to ensure fair evaluation and avoid data leakage,adopt a strict lesion-level partitioning strategy.Each image is first over-segmented using SLIC(Simple Linear Iterative Clustering)to produce perceptually homogeneous superpixels.These superpixels form the nodes of a region-adjacency graph whose edges encode spatial continuity.Node attributes are 1280-dimensional embeddings extracted with a lightweight yet expressive EfficientNet-B0 backbone,providing strong representational power at modest computational cost.The resulting graphs are processed by a five-layer Graph Attention Network(GAT)that learns to weight inter-node relationships dynamically and aggregates multi-hop context before classifying lesions into seven classes with a log-softmax output.Extensive experiments on the DermaMNIST benchmark show the proposed pipeline achieves 88.35%accuracy and 98.04%AUC,outperforming contemporary CNNs,AutoML approaches,and alternative graph neural networks.An ablation study indicates EfficientNet-B0 produces superior node descriptors compared with ResNet-18 and DenseNet,and that roughly five GAT layers strike a good balance between being too shallow and over-deep while avoiding oversmoothing.The method requires no data augmentation or external metadata,making it a drop-in upgrade for clinical computer-aided diagnosis systems.展开更多
Recently,self-supervised learning has shown great potential in Graph Neural Networks (GNNs) through contrastive learning,which aims to learn discriminative features for each node without label information. The key to ...Recently,self-supervised learning has shown great potential in Graph Neural Networks (GNNs) through contrastive learning,which aims to learn discriminative features for each node without label information. The key to graph contrastive learning is data augmentation. The anchor node regards its augmented samples as positive samples,and the rest of the samples are regarded as negative samples,some of which may be positive samples. We call these mislabeled samples as “false negative” samples,which will seriously affect the final learning effect. Since such semantically similar samples are ubiquitous in the graph,the problem of false negative samples is very significant. To address this issue,the paper proposes a novel model,False negative sample Detection for Graph Contrastive Learning (FD4GCL),which uses attribute and structure-aware to detect false negative samples. Experimental results on seven datasets show that FD4GCL outperforms the state-of-the-art baselines and even exceeds several supervised methods.展开更多
Prenatal depression,which can affect pregnant women’s physical and psychological health and cause postpartum depression,is increasing dramatically.Therefore,it is essential to detect prenatal depression early and con...Prenatal depression,which can affect pregnant women’s physical and psychological health and cause postpartum depression,is increasing dramatically.Therefore,it is essential to detect prenatal depression early and conduct an attribution analysis.Many studies have used questionnaires to screen for prenatal depression,but the existing methods lack attributability.To diagnose the early signs of prenatal depression and identify the key factors that may lead to prenatal depression from questionnaires,we present the semantically enhanced option embedding(SEOE)model to represent questionnaire options.It can quantitatively determine the relationship and patterns between options and depression.SEOE first quantifies options and resorts them,gathering options with little difference,since Word2Vec is highly dependent on context.The resort task is transformed into an optimization problem involving the traveling salesman problem.Moreover,all questionnaire samples are used to train the options’vector using Word2Vec.Finally,an LSTM and GRU fused model incorporating the cycle learning rate is constructed to detect whether a pregnant woman is suffering from depression.To verify the model,we compare it with other deep learning and traditional machine learning methods.The experiment results show that our proposed model can accurately identify pregnant women with depression and reach an F1 score of 0.8.The most relevant factors of depression found by SEOE are also verified in the literature.In addition,our model is of low computational complexity and strong generalization,which can be widely applied to other questionnaire analyses of psychiatric disorders.展开更多
Inductive knowledge graph embedding(KGE)aims to embed unseen entities in emerging knowledge graphs(KGs).The major recent studies of inductive KGE embed unseen entities by aggregating information from their neighboring...Inductive knowledge graph embedding(KGE)aims to embed unseen entities in emerging knowledge graphs(KGs).The major recent studies of inductive KGE embed unseen entities by aggregating information from their neighboring entities and relations with graph neural networks(GNNs).However,these methods rely on the existing neighbors of unseen entities and suffer from two common problems:data sparsity and feature smoothing.Firstly,the data sparsity problem means unseen entities usually emerge with few triplets containing insufficient information.Secondly,the effectiveness of the features extracted from original KGs will degrade when repeatedly propagating these features to represent unseen entities in emerging KGs,which is termed feature smoothing problem.To tackle the two problems,we propose a novel model entitled Meta-Learning Based Memory Graph Convolutional Network(MMGCN)consisting of three different components:1)the two-layer information transforming module(TITM)developed to effectively transform information from original KGs to emerging KGs;2)the hyper-relation feature initializing module(HFIM)proposed to extract type-level features shared between KGs and obtain a coarse-grained representation for each entity with these features;and 3)the meta-learning training module(MTM)designed to simulate the few-shot emerging KGs and train the model in a meta-learning framework.The extensive experiments conducted on the few-shot link prediction task for emerging KGs demonstrate the superiority of our proposed model MMGCN compared with state-of-the-art methods.展开更多
基金supported by the Science and Technology Program Project(No.2020A02001-1)of Xinjiang Autonomous Region,China.
文摘Smart contracts have led to more efficient development in finance and healthcare,but vulnerabilities in contracts pose high risks to their future applications.The current vulnerability detection methods for contracts are either based on fixed expert rules,which are inefficient,or rely on simplistic deep learning techniques that do not fully leverage contract semantic information.Therefore,there is ample room for improvement in terms of detection precision.To solve these problems,this paper proposes a vulnerability detector based on deep learning techniques,graph representation,and Transformer,called GRATDet.The method first performs swapping,insertion,and symbolization operations for contract functions,increasing the amount of small sample data.Each line of code is then treated as a basic semantic element,and information such as control and data relationships is extracted to construct a new representation in the form of a Line Graph(LG),which shows more structural features that differ from the serialized presentation of the contract.Finally,the node information and edge information of the graph are jointly learned using an improved Transformer-GP model to extract information globally and locally,and the fused features are used for vulnerability detection.The effectiveness of the method in reentrancy vulnerability detection is verified in experiments,where the F1 score reaches 95.16%,exceeding stateof-the-art methods.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Sciences(CAS)under Grant No.XDB0680302the National Key Research and Development Program of China under Grant No.2023YFC3305303+2 种基金the National Natural Science Foundation of China under Grant Nos.62372434 and 62302485the China Postdoctoral Science Foundation under Grant No.2022M713206the CAS Special Research Assistant Program,and the Key Research Project of Chinese Academy of Sciences under Grant No.RCJJ-145-24-21.
文摘Graph representation learning often faces knowledge scarcity in real-world applications,including limited labels and sparse relationships.Although a range of methods have been proposed to address these problems,such as graph few-shot learning,they mainly rely on inadequate knowledge within the task graph,which would limit their effectiveness.Moreover,they fail to consider other potentially useful task-related graphs.To overcome these limitations,domain adaptation for graph representation learning has emerged as an effective paradigm for transferring knowledge across graphs.It is also recognized as graph domain adaptation(GDA).In particular,to enhance model performance on target graphs with specific tasks,GDA introduces a bunch of task-related graphs as source graphs and adapts the knowledge learnt from source graphs to the target graphs.Since GDA combines the advantages of graph representation learning and domain adaptation,it has become a promising direction of transfer learning on graphs and has attracted an increasing amount of research interest in recent years.In this paper,we comprehensively overview the studies of GDA and present a detailed survey of recent advances.Specifically,we outline the current research status,analyze key challenges,propose a taxonomy,introduce representative work and practical applications,and discuss future prospects.To the best of our knowledge,this paper is the first survey for graph domain adaptation.
文摘Various graph representation learning models convert graph nodes into vectors using techniques like matrix factorization,random walk,and deep learning.However,choosing the right method for different tasks can be challenging.Communities within networks help reveal underlying structures and correlations.Investigating how different models preserve community properties is crucial for identifying the best graph representation for data analysis.This paper defines indicators to explore the perceptual quality of community properties in representation learning spaces,including the consistency of community structure,node distribution within and between communities,and central node distribution.A visualization system presents these indicators,allowing users to evaluate models based on community structures.Case studies demonstrate the effectiveness of the indicators for the visual evaluation of graph representation learning models.
基金supported by the MSIT(Ministry of Science and ICT),Republic of Korea,under the Convergence Security Core Talent Training Business Support Program(IITP-2025-RS-2023-00266605,50%)in part by the Institute of Information&Communications Technology Planning&Evaluation(lITP)grant funded by the Korea government(MSIT)(RS-2025-02305436,Development of Digital Innovative Element Technologies for Rapid Prediction of Potential Complex Disasters and Continuous Disaster Prevention,30%)supported by the Chung-Ang University Graduate Research Scholar-ship in 2023(20%).
文摘The escalating complexity and heterogeneity of modern energy systems—particularly in smart grid and distributed energy infrastructures—has intensified the need for intelligent and scalable security vulnerability classification.To address this challenge,we propose Vulnerability2Vec,a graph-embedding-based framework designed to enhance the automated classification of security vulnerabilities that threaten energy system resilience.Vulnerability2Vec converts Common Vulnerabilities and Exposures(CVE)text explanations to semantic graphs,where nodes represent CVE IDs and key terms(nouns,verbs,and adjectives),and edges capture co-occurrence relationships.Then,it embeds the semantic graphs to a low-dimensional vector space with random-walk sampling and skip-gram with negative sampling.It is possible to identify the latent relationships and structural patterns that traditional sparse vector methods fail to capture.Experimental results demonstrate a classification accuracy of up to 80%,significantly outperforming baseline methods.This approach offers a theoretical basis for classifying vulnerability types as structured semantic patterns in complex software systems.The proposed method models the semantic structure of vulnerabilities,providing a theoretical foundation for their classification.
文摘The proliferation of internet traffic encryption has become a double-edged sword. While it significantly enhances user privacy, it also inadvertently shields cyber-attacks from detection, presenting a formidable challenge to cybersecurity. Traditional machine learning and deep learning techniques often fall short in identifying encrypted malicious traffic due to their inability to fully extract and utilize the implicit relational and positional information embedded within data packets. This limitation has led to an unresolved challenge in the cybersecurity community: how to effectively extract valuable insights from the complex patterns of traffic packet transmission. Consequently, this paper introduces the TB-Graph model, an encrypted malicious traffic classification model based on a relational graph attention network. The model is a heterogeneous traffic burst graph that embeds side-channel features, which are unaffected by encryption, into the graph nodes and connects them with three different types of burst edges. Subsequently, we design a relational positional coding that prevents the loss of temporal relationships between the original traffic flows during graph transformation. Ultimately, TB-Graph leverages the powerful graph representation learning capabilities of Relational Graph Attention Network (RGAT) to extract latent behavioral features from the burst graph nodes and edge relationships. Experimental results show that TB-Graph outperforms various state-of-the-art methods in fine-grained encrypted malicious traffic classification tasks on two public datasets, indicating its enhanced capability for identifying encrypted malicious traffic.
基金This work was supported by the National Natural Science Foundation of China(No.22473001)the Natural Science Funds for Distinguished Young Scholar of Anhui Province(1908085J08)the University An-nual Scientific Research Plan of Anhui Province(2022AH010013).
文摘The performance of proton exchange membrane fuel cells depends heavily on the oxygen reduction reaction(ORR)at the cathode,for which platinum-based catalysts are currently the standard.The high cost and limited availability of platinum have driven the search for alternative catalysts.While FeN4 single-atom catalysts have shown promising potential,their ORR activity needs to be further enhanced.In contrast,dual-atom catalysts(DACs)offer not only higher metal loading but also the ability to break the ORR scaling relations.However,the diverse local structures and tunable coordination environments of DACs create a vast chemical space,making large-scale computational screening challenging.In this study,we developed a graph neural network(GNN)-based framework to predict the ORR activity of Fe-based DACs,effectively addressing the challenges posed by variations in local catalyst structures.Our model,trained on a dataset of 180 catalysts,accurately predicted the Gibbs free energy of ORR intermediates and overpotentials,and identified 32 DACs with superior catalytic activity compared to FeN4 SAC.This approach not only advances the design of high-performance DACs,but also offers a powerful computational tool that can significantly reduce the time and cost of catalyst development,thereby accelerating the commercialization of fuel cell technologies.
文摘Unsupervised learning methods such as graph contrastive learning have been used for dynamic graph represen-tation learning to eliminate the dependence of labels.However,existing studies neglect positional information when learning discrete snapshots,resulting in insufficient network topology learning.At the same time,due to the lack of appropriate data augmentation methods,it is difficult to capture the evolving patterns of the network effectively.To address the above problems,a position-aware and subgraph enhanced dynamic graph contrastive learning method is proposed for discrete-time dynamic graphs.Firstly,the global snapshot is built based on the historical snapshots to express the stable pattern of the dynamic graph,and the random walk is used to obtain the position representation by learning the positional information of the nodes.Secondly,a new data augmentation method is carried out from the perspectives of short-term changes and long-term stable structures of dynamic graphs.Specifically,subgraph sampling based on snapshots and global snapshots is used to obtain two structural augmentation views,and node structures and evolving patterns are learned by combining graph neural network,gated recurrent unit,and attention mechanism.Finally,the quality of node representation is improved by combining the contrastive learning between different structural augmentation views and between the two representations of structure and position.Experimental results on four real datasets show that the performance of the proposed method is better than the existing unsupervised methods,and it is more competitive than the supervised learning method under a semi-supervised setting.
基金supported in part by the National Natural Science Foundation of China under Grant 62272405,School and Locality Integration Development Project of Yantai City(2022)the Youth Innovation Science and Technology Support Program of Shandong Provincial under Grant 2021KJ080+2 种基金the Natural Science Foundation of Shandong Province,Grant ZR2022MF238Yantai Science and Technology Innovation Development Plan Project under Grant 2021YT06000645the Open Foundation of State key Laboratory of Networking and Switching Technology(Beijing University of Posts and Telecommunications)under Grant SKLNST-2022-1-12.
文摘With the rapid advancement of 5G technology,the Internet of Things(IoT)has entered a new phase of appli-cations and is rapidly becoming a significant force in promoting economic development.Due to the vast amounts of data created by numerous 5G IoT devices,the Ethereum platform has become a tool for the storage and sharing of IoT device data,thanks to its open and tamper-resistant characteristics.So,Ethereum account security is necessary for the Internet of Things to grow quickly and improve people's lives.By modeling Ethereum trans-action records as a transaction network,the account types are well identified by the Ethereum account classifi-cation system established based on Graph Neural Networks(GNNs).This work first investigates the Ethereum transaction network.Surprisingly,experimental metrics reveal that the Ethereum transaction network is neither optimal nor even satisfactory in terms of accurately representing transactions per account.This flaw may significantly impede the classification capability of GNNs,which is mostly governed by their attributes.This work proposes an Adaptive Multi-channel Bayesian Graph Attention Network(AMBGAT)for Ethereum account clas-sification to address this difficulty.AMBGAT uses attention to enhance node features,estimate graph topology that conforms to the ground truth,and efficiently extract node features pertinent to downstream tasks.An extensive experiment with actual Ethereum transaction data demonstrates that AMBGAT obtains competitive performance in the classification of Ethereum accounts while accurately estimating the graph topology.
基金supported by the Fundamental Research Funds for the Central Universities(Grant No.2022JKF02039).
文摘Graph Neural Networks(GNNs)play a significant role in tasks related to homophilic graphs.Traditional GNNs,based on the assumption of homophily,employ low-pass filters for neighboring nodes to achieve information aggregation and embedding.However,in heterophilic graphs,nodes from different categories often establish connections,while nodes of the same category are located further apart in the graph topology.This characteristic poses challenges to traditional GNNs,leading to issues of“distant node modeling deficiency”and“failure of the homophily assumption”.In response,this paper introduces the Spatial-Frequency domain Adaptive Heterophilic Graph Neural Networks(SFA-HGNN),which integrates adaptive embedding mechanisms for both spatial and frequency domains to address the aforementioned issues.Specifically,for the first problem,we propose the“Distant Spatial Embedding Module”,aiming to select and aggregate distant nodes through high-order randomwalk transition probabilities to enhance modeling capabilities.For the second issue,we design the“Proximal Frequency Domain Embedding Module”,constructing adaptive filters to separate high and low-frequency signals of nodes,and introduce frequency-domain guided attention mechanisms to fuse the relevant information,thereby reducing the noise introduced by the failure of the homophily assumption.We deploy the SFA-HGNN on six publicly available heterophilic networks,achieving state-of-the-art results in four of them.Furthermore,we elaborate on the hyperparameter selection mechanism and validate the performance of each module through experimentation,demonstrating a positive correlation between“node structural similarity”,“node attribute vector similarity”,and“node homophily”in heterophilic networks.
基金New-Generation Artificial Intelligence-Major Program in the Sci-Tech Innovation 2030 Agenda from the Ministry of Science and Technology of China(2018AAA0102100)Hunan Provincial Department of Education key project(21A0250)The First Class Discipline Open Fund of Hunan University of Traditional Chinese Medicine(2022ZYX08)。
文摘Objective To construct symptom-formula-herb heterogeneous graphs structured Treatise on Febrile Diseases(Shang Han Lun,《伤寒论》)dataset and explore an optimal learning method represented with node attributes based on graph convolutional network(GCN).Methods Clauses that contain symptoms,formulas,and herbs were abstracted from Treatise on Febrile Diseases to construct symptom-formula-herb heterogeneous graphs,which were used to propose a node representation learning method based on GCN−the Traditional Chinese Medicine Graph Convolution Network(TCM-GCN).The symptom-formula,symptom-herb,and formula-herb heterogeneous graphs were processed with the TCM-GCN to realize high-order propagating message passing and neighbor aggregation to obtain new node representation attributes,and thus acquiring the nodes’sum-aggregations of symptoms,formulas,and herbs to lay a foundation for the downstream tasks of the prediction models.Results Comparisons among the node representations with multi-hot encoding,non-fusion encoding,and fusion encoding showed that the Precision@10,Recall@10,and F1-score@10 of the fusion encoding were 9.77%,6.65%,and 8.30%,respectively,higher than those of the non-fusion encoding in the prediction studies of the model.Conclusion Node representations by fusion encoding achieved comparatively ideal results,indicating the TCM-GCN is effective in realizing node-level representations of heterogeneous graph structured Treatise on Febrile Diseases dataset and is able to elevate the performance of the downstream tasks of the diagnosis model.
基金supported by the National Natural Science Foundation of China under grants U19B2044National Key Research and Development Program of China(2021YFC3300500).
文摘Accurate prediction of future events brings great benefits and reduces losses for society in many domains,such as civil unrest,pandemics,and crimes.Knowledge graph is a general language for describing and modeling complex systems.Different types of events continually occur,which are often related to historical and concurrent events.In this paper,we formalize the future event prediction as a temporal knowledge graph reasoning problem.Most existing studies either conduct reasoning on static knowledge graphs or assume knowledges graphs of all timestamps are available during the training process.As a result,they cannot effectively reason over temporal knowledge graphs and predict events happening in the future.To address this problem,some recent works learn to infer future events based on historical eventbased temporal knowledge graphs.However,these methods do not comprehensively consider the latent patterns and influences behind historical events and concurrent events simultaneously.This paper proposes a new graph representation learning model,namely Recurrent Event Graph ATtention Network(RE-GAT),based on a novel historical and concurrent events attention-aware mechanism by modeling the event knowledge graph sequence recurrently.More specifically,our RE-GAT uses an attention-based historical events embedding module to encode past events,and employs an attention-based concurrent events embedding module to model the associations of events at the same timestamp.A translation-based decoder module and a learning objective are developed to optimize the embeddings of entities and relations.We evaluate our proposed method on four benchmark datasets.Extensive experimental results demonstrate the superiority of our RE-GAT model comparing to various base-lines,which proves that our method can more accurately predict what events are going to happen.
基金supported by the National Natural Science Foundation of China(No.61521003)
文摘Shortest-path calculation on weighted graphs are an essential operation in computer networks. The performance of such algorithms has become a critical challenge in emerging software-defined networks(SDN),since SDN controllers need to centralizedly perform a shortest-path query for every flow,usually on large-scale network. Unfortunately,one of the challenges is that current algorithms will become incalculable as the network size increases. Therefore, inspired by the compression graph in the field of compute visualization,we propose an efficient shortest path algorithm by compressing the original big network graph into a small one, but the important graph properties used to calculate path is reserved. We implement a centralized version of our approach in SDN-enabled network,and the evaluations validate the improvement compared with the well-known algorithms.
基金support by the National Natural Science Foundation of China(NSFC)under grant number 61873274.
文摘Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently.However,there are still two challenges.First,most of the real‐word system are multiple relations,where entities are linked by different types of relations,and each relation is a view of the graph network.Second,the rich multi‐scale information(structure‐level and feature‐level)of the graph network can be seen as self‐supervised signals,which are not fully exploited.A novel contrastive self‐supervised representation learning framework on attributed multiplex graph networks with multi‐scale(named CoLM^(2)S)information is presented in this study.It mainly contains two components:intra‐relation contrast learning and interrelation contrastive learning.Specifically,the contrastive self‐supervised representation learning framework on attributed single‐layer graph networks with multi‐scale information(CoLMS)framework with the graph convolutional network as encoder to capture the intra‐relation information with multi‐scale structure‐level and feature‐level selfsupervised signals is introduced first.The structure‐level information includes the edge structure and sub‐graph structure,and the feature‐level information represents the output of different graph convolutional layer.Second,according to the consensus assumption among inter‐relations,the CoLM^(2)S framework is proposed to jointly learn various graph relations in attributed multiplex graph network to achieve global consensus node embedding.The proposed method can fully distil the graph information.Extensive experiments on unsupervised node clustering and graph visualisation tasks demonstrate the effectiveness of our methods,and it outperforms existing competitive baselines.
基金supported by National Key Research and Development Pro-gram of China(No.2023YFC2206402)Youth Innovation Promotion Associa-tion CAS(No.2021156)+2 种基金the Strategic Priority Research Program of the Chinese Academy of Sciences(No.XDC02040100)Foundation Strengthening Program Technical Area Fund,021-JCJQ-JJ-0908State Grid Corporation of China Science and Technology Program(Contract No.:SG270000YXJS2311060).
文摘Advanced Persistent Threats (APTs) achieves internal networks penetration through multiple methods, making it difcult to detect attack clues solely through boundary defense measures. To address this challenge, some research has proposed threat detection methods based on provenance graphs, which leverage entity relationships such as processes, fles, and sockets found in host audit logs. However, these methods are generally inefcient, especially when faced with massive audit logs and the computational resource-intensive nature of graph algorithms. Efec-tivelyand economically extracting APT attack clues from massive system audit logs remains a signifcant challenge. To tackle this problem, this paper introduces the ProcSAGE method, which detects threats based on abnormal behavior patterns, ofering high accuracy, low cost, and independence from expert knowledge. ProcSAGE focuses on processes or threads in host audit logs during the graph construction phase to efectively control the scale of provenance graphs and reduce performance overhead. Additionally, in the feature extraction phase, ProcSAGE considers information about the processes or threads themselves and their neighboring nodes to accurately char-acterizethem and enhance model accuracy. In order to verify the efectiveness of the ProcSAGE method, this study conducted a comprehensive evaluation on the StreamSpot dataset. The experimental results show that the ProcSAGE method can signifcantly reduce the time and memory consumption in the threat detection process while improving the accuracy, and the optimization efect becomes more signifcant as the data size expands.
基金supported by the Shanghai Municipal Science and Technology Major Project[grant number 2021SHZD ZX0100]the Fundamental Research Funds for the Central Universities[grant number 2021SHZDZX0100].
文摘The outbreak and subsequent recurring waves of COVID−19 pose threats on the emergency management and people's daily life,while the large-scale spatio-temporal epidemiological data have sure come in handy in epidemic surveillance.Nonetheless,some challenges remain to be addressed in terms of multi-source heterogeneous data fusion,deep mining,and comprehensive applications.The Spatio-Temporal Artificial Intelligence(STAI)technology,which focuses on integrating spatial related time-series data,artificial intelligence models,and digital tools to provide intelligent computing platforms and applications,opens up new opportunities for scientific epidemic control.To this end,we leverage STAI and long-term experience in location-based intelligent services in the work.Specifically,we devise and develop a STAI-driven digital infrastructure,namely,WAYZ Disease Control Intelligent Platform(WDCIP),which consists of a systematic framework for building pipelines from automatic spatio-temporal data collection,processing to AI-based analysis and inference implementation for providing appropriate applications serving various epidemic scenarios.According to the platform implementation logic,our work can be performed and summarized from three aspects:(1)a STAI-driven integrated system;(2)a hybrid GNN-based approach for hierarchical risk assessment(as the core algorithm of WDCIP);and(3)comprehensive applications for social epidemic containment.This work makes a pivotal contribution to facilitating the aggregation and full utilization of spatio-temporal epidemic data from multiple sources,where the real-time human mobility data generated by high-precision mobile positioning plays a vital role in sensing the spread of the epidemic.So far,WDCIP has accumulated more than 200 million users who have been served in life convenience and decision-making during the pandemic.
基金supported by the National Natural Science Foundation of China(Nos.72293575,62071467 and 62141608).
文摘Identifying personalities accurately helps merchants and management departments understand user needs in detail and improve the quality of service and decision-making efficiency.Existing research on text-based personality prediction mainly uses deep neural networks or pretrained language models to mine deep semantics,ignoring the dynamic interactions among personality features.This paper presents a novel personality prediction method that simultaneously taps into the capability of graph neural networks to model the deep interactions among features and that of pretrained language models to learn latent semantics with a hierarchical aggregation mechanism.Specifically,the proposed model leverages self-attention to capture the interaction relationships among POS tags,entities,personality tags,etc.,and considers the labels’cooccurrence patterns.The efficacy of the proposed model is evaluated on the myPersonality and PANDORA datasets.This research contributes to the personality prediction literature from the perspective of a multigranular personality feature learning perspective and provides business value for consuming predictive analytics.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2025-02-01296).
文摘Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and severe class imbalance,and occasional imaging artifacts can create ambiguity for state-of-the-art convolutional neural networks(CNNs).We frame skin lesion recognition as graph-based reasoning and,to ensure fair evaluation and avoid data leakage,adopt a strict lesion-level partitioning strategy.Each image is first over-segmented using SLIC(Simple Linear Iterative Clustering)to produce perceptually homogeneous superpixels.These superpixels form the nodes of a region-adjacency graph whose edges encode spatial continuity.Node attributes are 1280-dimensional embeddings extracted with a lightweight yet expressive EfficientNet-B0 backbone,providing strong representational power at modest computational cost.The resulting graphs are processed by a five-layer Graph Attention Network(GAT)that learns to weight inter-node relationships dynamically and aggregates multi-hop context before classifying lesions into seven classes with a log-softmax output.Extensive experiments on the DermaMNIST benchmark show the proposed pipeline achieves 88.35%accuracy and 98.04%AUC,outperforming contemporary CNNs,AutoML approaches,and alternative graph neural networks.An ablation study indicates EfficientNet-B0 produces superior node descriptors compared with ResNet-18 and DenseNet,and that roughly five GAT layers strike a good balance between being too shallow and over-deep while avoiding oversmoothing.The method requires no data augmentation or external metadata,making it a drop-in upgrade for clinical computer-aided diagnosis systems.
基金supported by the National Key Research and Development Program of China(No.2021YFB3300503)Regional Innovation and Development Joint Fund of National Natural Science Foundation of China(No.U22A20167)National Natural Science Foundation of China(No.61872260).
文摘Recently,self-supervised learning has shown great potential in Graph Neural Networks (GNNs) through contrastive learning,which aims to learn discriminative features for each node without label information. The key to graph contrastive learning is data augmentation. The anchor node regards its augmented samples as positive samples,and the rest of the samples are regarded as negative samples,some of which may be positive samples. We call these mislabeled samples as “false negative” samples,which will seriously affect the final learning effect. Since such semantically similar samples are ubiquitous in the graph,the problem of false negative samples is very significant. To address this issue,the paper proposes a novel model,False negative sample Detection for Graph Contrastive Learning (FD4GCL),which uses attribute and structure-aware to detect false negative samples. Experimental results on seven datasets show that FD4GCL outperforms the state-of-the-art baselines and even exceeds several supervised methods.
基金the National Key R&D Program of China(No.2021YFF1201200)the National Natural Science Foundation of China(Grant Nos.61972174 and 62172187)+1 种基金the Science and Technology Planning Project of Jilin Province(No.20220201145GX,No.20200708112YY and No.20220601112FG)the Science and Technology Planning Project of Guangdong Province(No.2020A0505100018),Guangdong Universities’Innovation Team Project(No.2021KCXTD015)and Guangdong Key Disciplines Project(No.2021ZDJS138)。
文摘Prenatal depression,which can affect pregnant women’s physical and psychological health and cause postpartum depression,is increasing dramatically.Therefore,it is essential to detect prenatal depression early and conduct an attribution analysis.Many studies have used questionnaires to screen for prenatal depression,but the existing methods lack attributability.To diagnose the early signs of prenatal depression and identify the key factors that may lead to prenatal depression from questionnaires,we present the semantically enhanced option embedding(SEOE)model to represent questionnaire options.It can quantitatively determine the relationship and patterns between options and depression.SEOE first quantifies options and resorts them,gathering options with little difference,since Word2Vec is highly dependent on context.The resort task is transformed into an optimization problem involving the traveling salesman problem.Moreover,all questionnaire samples are used to train the options’vector using Word2Vec.Finally,an LSTM and GRU fused model incorporating the cycle learning rate is constructed to detect whether a pregnant woman is suffering from depression.To verify the model,we compare it with other deep learning and traditional machine learning methods.The experiment results show that our proposed model can accurately identify pregnant women with depression and reach an F1 score of 0.8.The most relevant factors of depression found by SEOE are also verified in the literature.In addition,our model is of low computational complexity and strong generalization,which can be widely applied to other questionnaire analyses of psychiatric disorders.
基金supported by the National Natural Science Foundation of China under Grant No.62272332the Major Program of the Natural Science Foundation of Jiangsu Higher Education Institutions of China under Grant No.22KJA520006.
文摘Inductive knowledge graph embedding(KGE)aims to embed unseen entities in emerging knowledge graphs(KGs).The major recent studies of inductive KGE embed unseen entities by aggregating information from their neighboring entities and relations with graph neural networks(GNNs).However,these methods rely on the existing neighbors of unseen entities and suffer from two common problems:data sparsity and feature smoothing.Firstly,the data sparsity problem means unseen entities usually emerge with few triplets containing insufficient information.Secondly,the effectiveness of the features extracted from original KGs will degrade when repeatedly propagating these features to represent unseen entities in emerging KGs,which is termed feature smoothing problem.To tackle the two problems,we propose a novel model entitled Meta-Learning Based Memory Graph Convolutional Network(MMGCN)consisting of three different components:1)the two-layer information transforming module(TITM)developed to effectively transform information from original KGs to emerging KGs;2)the hyper-relation feature initializing module(HFIM)proposed to extract type-level features shared between KGs and obtain a coarse-grained representation for each entity with these features;and 3)the meta-learning training module(MTM)designed to simulate the few-shot emerging KGs and train the model in a meta-learning framework.The extensive experiments conducted on the few-shot link prediction task for emerging KGs demonstrate the superiority of our proposed model MMGCN compared with state-of-the-art methods.
