79 results about "Graph classification" patented technology

The invention belongs to the technical field of graph classification, discloses a graph classification method based on subgraph integration and position sensing, and relates to a graph classification method SIPA combining substructure embedding and node position sensing. The SIPA firstly extracts sub-graphs through two different strategies so as to capture multi-sample sub-structures in the graphs, the structural features of the sub-structures are coded by adopting a graph convolutional network, and information of different sub-graphs is effectively fused through an attention mechanism. Then, anchor nodes are introduced to calculate relative position information of nodes, and the information is embedded into node representation to better capture global position features. And finally, a graph information bottleneck mechanism is used for optimizing node representation and removing redundant information irrelevant to a classification task. The method not only effectively learns the local structure information, but also enhances the perception capability of the relative position information of the nodes. Experimental results show that SIPA is superior to an existing baseline model in five data sets, and the superiority of SIPA in a graph classification task is verified.

The invention relates to a graph model fine tuning method based on graph prompt learning, and aims to solve the problem that a graph model pre-training task is inconsistent with a downstream task target and improve the performance of tasks such as node classification and graph classification. The method comprises the following steps of: firstly, sampling graph data by restarting random walk, and learning a pre-training model through graph-level contrast to fully mine graph representation capability; secondly, aiming at a downstream node classification task, extracting a two-hop neighborhood construction induction graph for each target node, and selecting the most representative dominating node based on the minimum dominating set; further, in order to enhance hierarchy and discrimination of the graph structure, a corresponding sub-graph-level node is introduced for each dominating node, a global graph-level node is added, and a unified prompt graph is constructed by connecting the dominating nodes with the corresponding sub-graph-level nodes and connecting all the sub-graph-level nodes to the graph-level nodes. And then, in a representation generation stage, fusing information of different granularities through a multi-level graph embedding aggregation strategy, and weighting to obtain final graph-level embedding representation. And finally, performing similarity calculation on the graph representation and a predefined class prototype, and selecting a class with the highest similarity as a target node prediction result, thereby converting a node classification task into a graph classification task. According to the method, the performance is excellent when upstream and downstream task targets are unified, the pre-training encoder is frozen during fine adjustment, and only relevant parameters of the prompt weight are updated, so that the model performance, the adaptability and the practical value are remarkably improved.

The invention discloses an abnormal transaction dynamic detection method and system fusing multi-scale analysis and information entropy, and the method comprises the steps: S01, constructing a dynamic heterogeneous graph which comprises account nodes, equipment nodes and IP nodes; s02, extracting node features of each node, extracting a spectrum feature matrix of the dynamic heterogeneous graph, and forming a node feature vector of each node; step S03, clustering the dynamic heterogeneous graph to screen out candidate detection sub-graphs, inputting node feature vectors of nodes in the candidate detection sub-graphs into a pre-trained graph classification model, and identifying an abnormal account node set; and S04, calculating a corresponding dynamic risk score in real time according to the memory state vector of each abnormal account node in the time sequence diagram network and the diagram information entropy change rate so as to evaluate a real-time risk and identify a core abnormal account. According to the method, the group type abnormal transaction account can be quickly and accurately identified, and the core abnormal account can be positioned.

The invention discloses a smart contract state manipulation attack detection method, system and device based on a graph neural network, and a medium, and belongs to the technical field of block chain security analysis, and the method comprises the steps: defining a smart contract state manipulation attack type, collecting an attacked smart contract and a normal smart contract on a block chain, and constructing a training data set; positioning a creator of the target smart contract, and constructing a historical external transaction graph; decompiling the target smart contract, and constructing an external calling behavior graph; combining the historical external transaction graph with the external calling behavior graph to construct a creation behavior graph of the smart contract; constructing a classifier of a state manipulation attack; and monitoring the smart contract created in real time, constructing and creating a behavior graph, and inputting the behavior graph into the classifier to realize real-time detection of the state manipulation attack. According to the method, the blockchain nodes can be connected, the newly deployed smart contract is acquired in real time, and the smart contract creation behavior graph is constructed and input into the graph classification model to realize detection of the state manipulation attack smart contract.

The invention relates to a test time training method based on invariant graph learning, and the method comprises the following steps: 1, a joint training stage, a joint training encoder fg, a main task classification head pi m and self-supervision task classification heads pi s1 and pi s2 are trained through a graph classification task and an auxiliary self-supervision task by using marked training set data, and the joint training stage is divided into two parts including invariant graph recognition and multi-level graph comparison learning; step 2, in a test time training stage, realizing self-adaption of the model on test data by minimizing the difference of feature distribution of a training domain and a test domain; and step 3, a test stage: in a model test stage, carrying out specific processes and strategies of model evaluation and fine adjustment by using a test sample. According to the scheme, through a test time training method, the model is finely adjusted by using label-free test data distribution, and the generalization performance of the model in a distribution offset scene is improved.

A domain-generalized person re-identification method and system based on meta-graph awareness includes: a ResNet50 network as the backbone network, a meta-global correlation awareness module, a meta-graph relationship sampling module, and a person matching module. This invention applies the Meta-Graph Aware (M-GRA) algorithm to domain-generalized person re-identification. In the meta-training domain, all block features are stacked using an affinity model to construct pairwise relationships. Then, a shallow convolutional model is used to learn this feature stacking relationship model, and a global knowledge graph is constructed. This classifies and weights structural information, suppressing noise while maintaining learning efficiency, and preventing model overfitting.

The application discloses a kind of graph classification training methods based on supervised contrast learning and structure inference, first, the model is fully mined by structure inference Topological information of graph data itself as originally graph data Enhanced graph.Then through label random sampling constructs sample positive-negative example pair, and using hierarchical graph neural network respectively to positive-negative example sample learning to extract whole graph embedding.Finally, through ordinary classification loss and supervised contrast learning loss jointly guide the learning process of hierarchical graph neural network, improve the classification performance of embedding.The application fuses structure inference and label information, the data enhancement mode based on structure inference does not need prior knowledge, expands the scope of model use, accelerates model learning speed.Self-supervised contrast learning on graph data is extended to contrast learning under label supervision, enhances its contrast learning ability.The application improves graph classification performance, and has good generalizability on generalized graph classification data.

Methods, systems, and non-transitory computer readable storage media are disclosed for dynamically generating and modifying interactive graph-based taxonomies associated with data processes in various domains. The disclosed system generates node data objects representing a domain-category hierarchy in connection with one or more computing data processes via a library of tools. The disclosed systems generates an attribute data object corresponding to an attribute assigned to a node data object in the graph-based taxonomy and links the attribute data object to node data objects according to parent / child relationships of the hierarchy. The disclosed system utilizes the parent / child relationships of the node data objects and attribute data object to aggregate attribute values of the attributes according to one or more aggregation operations. The disclosed systems provide indications of the aggregated attribute values for display via a graphical user interface for use in performing data processes.

This application relates to the field of integrated circuit design automation technology, and provides a method and system for verifying analog circuit structures based on graph neural networks. The method includes: converting a SPICE netlist into a graph structure representation, where nodes correspond to devices and edges correspond to electrical connections, and extracting feature vectors containing device type, parameters, functional roles, connection types, and signal directions; encoding the circuit diagram using a graph attention network to obtain node embeddings and graph embeddings; performing multi-task prediction based on the embedding results, including node classification, graph classification, structure scoring, and error localization; and finally generating a verification report containing an error list, location information, and repair suggestions. This application achieves automatic detection and precise localization of errors in analog circuit structures, improving detection accuracy by a significant margin and possessing strong generalization capabilities.

The invention provides a node identification method and device based on graph classification and a related product, and relates to the technical field of data processing. The method comprises the following steps: calling a preset connected sub-graph recognition algorithm to recognize one or more connected sub-graphs of which the node number is greater than a set threshold value in a social network to obtain a connected sub-graph set; extracting a user node in the connected sub-graph, and extracting a local structure of the user node in the global network, namely a user case sub-graph taking the user node as a center; then classifying the user case sub-graphs by using a pre-trained graph convolutional network dichotomy model; in this way, user node recognition is converted into recognition of the local network where the user node is located, the user case sub-graphs with the user node as the center are classified through the pre-trained graph convolutional network dichotomy model, and therefore the classification result of the user node is obtained, the calculation amount is greatly reduced, and the recognition accuracy and efficiency are improved.

The application discloses a graph classification method based on a saliency regularization graph neural network and related devices. The method comprises obtaining graph structure data corresponding to a target to be classified, and inputting the graph structure data into a saliency regularization graph neural network; determining a classification category of the target to be classified through the saliency regularization graph neural network; wherein the saliency regularization graph neural network learns a node feature matrix through a skeleton network, extracts the node feature matrix into a compact graph feature representation through a graph neural memory network, determines a saliency distribution vector based on the compact graph feature representation and the node feature matrix, and finally normalizes the aggregation weight of the skeleton network through the saliency distribution vector. In this way, the saliency regularization graph neural network focuses on the nodes more related to graph classification by measuring the compatibility between the entire compact graph feature representation and the node feature matrix, and can learn a more effective representation for the entire graph, thereby improving the classification effect of the graph classification task.

The invention discloses a graph classification method based on multi-view adaptive attention and feature integration enhancement, and aims to improve the representation capability and classification performance of graph structure data. An existing image classification method generally has the problems of single feature extraction view angle and inflexible fusion mechanism, and multi-level structure information in an image is difficult to fully mine. Therefore, the method has the following characteristics and contributions: firstly, a feature integration module fusing multi-graph convolution and one-dimensional convolution is constructed, graph node features are extracted from different view angles through multiple graph convolution, and self-adaptive integration of cross-view-angle features is realized by means of the one-dimensional convolution; secondly, designing a multi-angle adaptive channel attention mechanism, dynamically calculating weight distribution of each channel, and emphatically strengthening information expression of key semantic channels; finally, experimental verification on eight public graph classification data sets shows that the average classification accuracy of the method is improved by about 10% compared with that of a current advanced method, and the superiority and practicability of the method in a graph classification task are effectively proved.

The application discloses a personalized federated graph learning method and system suitable for cross-domain graph classification, and general graph spectrum knowledge is shared in view of the influence of structural heterogeneity in global cooperation, the general spectrum knowledge is shared in a global spectrum encoder including a global feature value encoder and a global filtering encoder, and customers benefit from the cooperation; wherein, other components representing non-general knowledge are reserved locally, each customer customizes personalized graph convolution for its own graph characteristics, and negative influence of spectrum bias is avoided; in view of the influence of structural heterogeneity in local application, a learnable preference is configured for each customer, a personalized preference module is used to cooperate with the work of the global spectrum encoder, personalized graph preference adjustment is performed, and the personalized graph preference adjustment is adapted to the unique graph structure of each customer; wherein, a regularization term is used to limit the personalized preference module to focus on local preference, and an over-reliance problem caused by the regularization term is solved.

The present application relates to a kind of decoupling knowledge distillation hardware target detection method and system, method includes: according to data set mark frame in first model and second model respectively, decoupling is carried out to mark data set, and the foreground target area and background area are obtained, to determine the target kind probability of hardware, and according to target kind probability determine common feature score mask;According to common feature score mask and feature map classification score graph determine first distillation loss function;Based on global context module, according to the determination feature map, construct second distillation loss function;According to each distillation loss function, determine total loss function, and according to total loss function, the second model is trained, to carry out target detection to the hardware image to be measured.The present application uses the common shape feature of different kinds of hardware, adopts decoupling knowledge distillation method, for foreground target area, the common feature belonging to the unique hardware between is used for the information integration of target classification to migrate to small model, improves hardware detection precision.

The invention discloses a virus sample classification method and system based on a graph classification algorithm. The method comprises the following steps: firstly, collecting image samples of various virus categories, and carrying out preprocessing operation; secondly, performing data enhancement on the preprocessed image data, and constructing a classification model based on a VGG16 model architecture; training the constructed classification model, evaluating the performance of the classification model on a verification set, adjusting a training strategy according to an evaluation result, and optimizing the performance of the model; then acquiring a to-be-detected virus sample image, preprocessing the to-be-detected virus sample image, and classifying the to-be-detected virus sample image by using the trained virus sample classification model; and finally, outputting a classification result, and carrying out encrypted storage and safe deployment on the trained virus sample classification model. According to the method, the accuracy and efficiency of virus sample classification are effectively improved, the generalization ability of the model is enhanced, a large number of virus samples can be rapidly processed, and the real-time requirement in practical application is met.

The application belongs to the field of graph neural network interpretation, and particularly relates to an interpretable molecular property prediction method based on a graph neural network, which comprises the following steps: acquiring graph data G, iteratively processing the graph data, and generating K key subgraphs; acquiring a graph neural network graph classification model, and acquiring node embedding according to the graph neural network graph classification model; obtaining an edge mask matrix of the graph according to the node embedding; inputting the K key subgraphs and the mask matrix into a perceiver to score the importance of each key subgraph, obtaining a score matrix W and a belonging relationship matrix L of each edge in the graph G and a key subgraph mode; inputting the score matrix W and the belonging relationship matrix into a mask updater, and obtaining a final mask matrix M; and selecting topK edges with the highest mask values from the mask matrix M to generate an explanation subgraph as an explanation of the graph neural network graph classification model; and the frequent subgraph mining algorithm is used to extract important subgraph modes in the data, so that the interpretable accuracy is improved.

This invention discloses a method for tracking and tracing sensitive network behaviors, relating to the field of network security technology. The specific steps of this method are as follows: collecting and preprocessing multi-source heterogeneous data in the network environment and storing it in a distributed database; constructing a cross-modal semantic graph using a large language model; training an intent classification model to predict sensitive behavior intents and forming an association set; locating intent trigger points and constructing a complete tracing chain through an intent trigger point causal contribution algorithm; integrating data to generate a standardized tracing report, and presenting it through a visualization tool, supporting interaction and export. This invention first integrates and analyzes multi-source heterogeneous data to construct a cross-modal semantic graph, accurately identifies sensitive behavior intents through model training and filtering, then locates intent trigger points through algorithms, constructs a tracing chain, and finally outputs a visualized report, forming an easy-to-understand report, thus improving the comprehensiveness, accuracy, and convenience of sensitive behavior identification and tracing.

The application discloses a sea surface target detection method based on data enhancement and recursive graph classification of a Transform technology and belongs to the field of radar target detection. The sea surface target detection method comprises the following steps: obtaining a sea surface echo amplitude sequence by using a radar, pre-processing the sea surface echo amplitude sequence to obtain radar measured target echo amplitude data, and processing the radar measured target echo amplitude data into a data format suitable for being input into a Transform; generating historical item data and future item data of the measured target amplitude by using a Transform bidirectional prediction mechanism according to the pre-processed measured target amplitude data, and splicing the historical item data and the future item data with the measured target amplitude data to obtain enhanced target amplitude data; constructing the enhanced measured target amplitude data into a recursive graph data set; training the recursive graph data set by using a convolutional neural network to obtain a classifier model; and classifying a to-be-detected recursive graph by using the classifier model and outputting a classification result.

The application belongs to the field of artificial intelligence, and discloses an instance-level graph prompt and label attention distillation graph classification method, comprising S1, data preparation: obtaining a graph data set, extracting node features and graph structures of each graph sample, and dividing the data set into a training set, a validation set and a test set; S2, teacher model training: constructing a teacher graph neural network model with double prompts and training; S3, student model distillation training: the training target includes fitting the real label of the classification result output by the student model, and approximating the teacher graph-level embedding output by the teacher model to the graph-level embedding generated by the student model; S4, performance evaluation: using the test set to evaluate the graph classification performance of the trained student model. The application adaptively fuses multi-source information through a weight learning module, and adopts a pre-training-teacher-student three-stage training framework, which significantly improves the classification accuracy, model generalization ability and deployment efficiency.

The application discloses a kind of based on multilayer perceptron's graph classification model construction method and graph classification method, the former includes: the classification task of required application scene is acquired to several graph data and constitutes training set;At least part of graph data of training set has class label;Using training set, selected graph neural network is trained, and the graph neural network that training is completed is used as teacher network and saves the classification result corresponding to graph neural network;Selected multilayer perceptron is used as student model, based on training set, teacher network and corresponding classification result, student model is trained using the method of knowledge distillation, and the student model that training is completed is used as graph classification model for the remaining graph data classification of required application scene.The graph classification model of the application combines the respective advantages of multilayer perceptron and graph neural network, without the dependency of graph in reasoning process, ensure higher accuracy while can greatly reduce model calculation complexity, improve reasoning speed, can be used for time limited engineering deployment.

The application relates to a design method of a granule-based quantum graph neural network for graph classification, and belongs to the field of quantum machine learning. The method comprises the following steps: S1: a classical granule generation method is used to generate granule samples from data samples; S2: a node data set and an edge data set are acquired, and encoding and preparation are completed; S3: a variational quantum wire is designed to enhance node features; S4: a quantum graph convolution circuit is designed to realize information transmission and parameter sharing between nodes; S5: a quantum graph pooling circuit is designed to extract multiple quantum bit information onto one quantum bit, so that feature dimension reduction is realized; S6: training set is input to train parameters of the whole model; and S7: a to-be-tested data set is input to the model, a Pauli Z measurement is performed on a specified quantum bit to obtain an expected value, and finally, graph classification is completed. The application reduces the number of data sample points, overcomes the defect that a large amount of data cannot be prepared in a quantum experiment, and optimizes the quantum graph convolution circuit and the quantum graph pooling circuit.

Embodiments of the present systems and methods may provide techniques to predict the success or failure of a drug used for disease treatment. For example, a method of determining drug efficacy may include, for a plurality of patients, generating a directed acyclic graph from health related information of each patient comprising nodes representing a medical event of the patient, at least one first edge connecting the first node to an additional node, each additional edge connecting nodes representing two consecutive medical events, the edge having a weight based on a time difference between the two consecutive medical events, capturing a plurality of features from each directed acyclic graph, generating a binary graph classification model on captured features of each directed acyclic graph, determining a probability that a drug or treatment will be effective using the binary graph classification model, and determining a drug to be prescribed to a patient based on the determined probability.

The invention provides a sub-graph reconstruction method for unbalanced graph classification, which can be applied to the technical field of graph neural networks. The method comprises the following steps: identifying minority class nodes in an original graph, and clustering the minority class nodes to obtain at least one local dense cluster; at least one hub node is generated for each cluster, the hub nodes are added into the graph, and each hub node is in-cluster connection with the nodes in the cluster which the hub node belongs to and is in cross-cluster connection with the nodes of other clusters or the hub nodes; selecting seed nodes from the minority class nodes based on preset significance measurement; at least one synthesis node is generated for each seed node, the synthesis nodes are added into the graph, and each synthesis node is connected with a corresponding source seed node and a node adjacent to the source seed node; taking the graph added with the hub nodes and the composite nodes as an expansion graph, and carrying out graph neural network training; wherein a joint loss function is adopted in the training process.

The invention provides an explainable graph neural network method and system based on evidence sub-graph extraction, which are used for improving the explainability and robustness of a graph model while keeping the task prediction performance. In order to solve the problem that information loss and shortcut residues are easily caused due to the fact that single-stage decomposition is too rough in an existing graph evidence technology, the invention provides a two-step decomposition and feature alignment graph evidence framework. According to the framework, firstly, an input graph is divided into an important sub-graph and a noise sub-graph through a first decomposition module, and it is ensured that the important sub-graph can independently complete tasks; on the basis, the second decomposition module further divides the important sub-graph into an evidence sub-graph and a shortcut sub-graph, so that shortcut associated information influencing the generalization ability of the model is eliminated, and an evidence structure supporting a prediction decision is obtained. Meanwhile, a feature mask is introduced to carry out information compensation, and InfoNCE alignment loss between a mask pattern and evidence representation is calculated, so that information loss caused by multi-level decomposition is reduced. And finally realizing compact expression of the evidence sub-graph through sparsity constraint. The method can effectively obtain evidence sub-graph representation with strong discrimination ability, high robustness and high interpretability, is suitable for tasks such as graph classification, and can be deployed in application scenes such as judicial analysis and drug discovery requiring high-credibility interpretation.

The application relates to a trusted subgraph mining method based on subgraph generation, which comprises the following steps: randomly selecting a drug molecule graph structure, using breadth-first search sampling to obtain I first molecular relationship subgraphs, generating a corresponding negative example subgraph for each first molecular relationship subgraph, using a graph neural network GraphSAGE to encode positive and negative samples into an ordered vector space, training a graph embedding generation model through a loss function, using a greedy strategy to add nodes one by one to generate a target subgraph, inputting the target subgraph into a pre-trained GNN graph classification model, and screening out a target subgraph with the maximum probability of being predicted as a target class by the model as a trusted subgraph; the application can find a trusted subgraph with the maximum probability of being predicted as a target class by a GNN graph classification model, and can assist personnel in a related field in decision-making, such as drug discovery and the like.

A method for providing event-specific intervention recommendations includes identifying, based on an event trigger, one or more sensors, determining, by processing data streams provided by the identified sensors, a set of event related entities and constructing, for each entity of the determined set of entities, an associated feature vector of the entity's features, generating, based on the determined entities and their respective feature vector, an entity-feature-graph, computing, by performing graph classification of a predefined set of allowed interventions based on a trained graph classification model, a ranked list of interventions; and selecting, according to predefined rules, one or more interventions from the ranked list of interventions and providing the selected interventions as recommended interventions for execution. The method can be used to support decision making.

The invention relates to a small sample intention recognition method based on multi-view logistic regression, belongs to the technical field of artificial intelligence and natural language processing, and solves the problems that an existing small sample intention classification method is insufficient in example selection, semantic similar intentions are difficult to distinguish and the model generalization ability is limited. According to the technical scheme, the method comprises the steps that semantic embedding processing is conducted on training data and query statements, cosine similarity is calculated, the size K of an initial support set is dynamically determined based on semantic uncertainty, first K examples are selected to form the initial support set, a multi-view logistic regression model is applied to conduct embedding space discriminative conversion, similarity is recalculated, and the initial support set is selected. And carrying out diversity constraint optimization on the final support set by adopting a maximum and minimum distance selection algorithm, and constructing large language model input for intention recognition. According to the method, the most discriminative and representative examples can be automatically screened, and the classification accuracy, robustness and generalization ability are improved.

The application provides a kind of based on betweenness centrality and geometric consistency graph contrast learning method and device, it is related to graph classification technical field.The method includes: according to the betweenness centrality of graph data node and edge, enhanced graph data is constructed to delete probability;Get the node feature of graph data and enhanced graph data, obtain graph representation by aggregating node feature based on Gaussian kernel reading method;According to the topological structure and node feature of graph data, construct multi-scale geometric consistency loss, construct normalized temperature scale cross-entropy loss according to graph representation, and then construct total loss to realize graph classification.The application introduces graph betweenness centrality into graph contrast learning, so as to retain important structural information of graph in graph enhancement process;Introducing multi-scale geometric consistency loss makes the structure information of graph can better guide the generation of graph feature;Optimize aggregated node feature based on Gaussian kernel reading method to obtain complete graph representation, to obtain more discriminative graph-level features.

The application discloses a few-shot graph classification method based on track enhancement and residual prompt, relates to the technical field of artificial intelligence and graph deep learning, and is suitable for molecular property prediction, drug screening and other graph learning tasks. The method obtains node structure roles through graph element track statistics, constructs a track correlation matrix and performs random walk in a track topological space, generates a track enhanced view to extract high-order topological semantics, introduces a learnable global prototype in the pre-training stage, uniformly constrains the prototype probability distribution of the original view and the track enhanced view, thereby learning a more stable graph encoder for the structure mode, in the downstream stage, track anchor representations are aggregated from a small number of class samples, and the anchor representations are parameterized to generate a probability prompt representation, a graph prompt vector is obtained in a differentiable manner, and the weighted aggregation and classification prediction of the node-level representation are guided. The application can adapt to the distribution difference within the class, and improve the generalization performance and robustness under the few-shot condition.

The invention relates to a multi-frequency gated chart LCZ classification method based on a multi-view satellite image, and belongs to the field of remote sensing image scene classification. The method comprises the steps that multi-angle features are added into an original multispectral image data set, a multi-angle image is obtained and input into a designed frequency domain gating module, image space features and image frequency domain features are extracted through parallel processing of a deformable gating branch and a frequency domain transformation branch, and the two features are fused through a fusion module; and inputting the fusion features into a graph convolution module, remodeling the fusion features into a graph structure, performing graph convolution coding, and finally obtaining an LCZ classification result. According to the method, a double-branch structure and graph convolution are designed for the first time and used for feature extraction of multi-view remote sensing images, a multi-angle stereoscopic feature extraction module is designed to fully capture three-dimensional features of ground features, and LCZ classification precision is greatly improved.