中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

18 records (took 0.024 seconds)

    MEMORY-AUGMENTED GRAPH CONVOLUTIONAL NEURAL NETWORKS
    2.
    发明申请
    MEMORY-AUGMENTED GRAPH CONVOLUTIONAL NEURAL NETWORKS 有权

    公开(公告)号：US20230027427A1

    公开(公告)日：2023-01-26

    申请号：US17370889

    申请日：2021-07-08

    Applicant: Liheng MA ,  Yingxue ZHANG ,  Mark COATES

    Inventor： Liheng MA ,  Yingxue ZHANG ,  Mark COATES

    IPC: G06N3/08 ,  G06K9/62

    Abstract: System and method for processing a graph that defines a set of nodes and a set of edges, the nodes each having an associated set of node attributes, the edges each representing a relationship that connects two respective nodes, comprising: generating a first node embedding for each node by: generating, for the node and each of a plurality of neighbour nodes, a respective first edge attribute defining a respective relationship type between the node and the neighbour node based on the node attributes of the node and the node attributes of the neighbour node; generating a first neighborhood vector that aggregates information from the generated first edge attributes and the node attributes of the neighbour nodes; generating the first node embedding based on the node attributes of the node and the generated first neighborhood vector.

    METHODS AND SYSTEMS FOR CONGESTION PREDICTION IN LOGIC SYNTHESIS USING GRAPH NEURAL NETWORKS
    3.
    发明申请
    METHODS AND SYSTEMS FOR CONGESTION PREDICTION IN LOGIC SYNTHESIS USING GRAPH NEURAL NETWORKS 有权

    公开(公告)号：US20220405455A1

    公开(公告)日：2022-12-22

    申请号：US17334657

    申请日：2021-05-28

    Applicant: Amur GHOSE ,  Yingxue ZHANG ,  Zhanguang ZHANG

    Inventor： Amur GHOSE ,  Yingxue ZHANG ,  Zhanguang ZHANG

    IPC: G06F30/392 ,  G06F30/398 ,  G06N3/08 ,  G06K9/62

    Abstract: Method and system for assisting electronic chip design, comprising: receiving netlist data for a proposed electronic chip design, the netlist data including a list of circuit elements and a list of interconnections between the circuit elements; converting the netlist data to a graph that represents at least some of the circuit elements as nodes and represents the interconnections between the circuit elements as edges; extracting network embeddings for the nodes based on a graph topology represented by the edges; extracting degree features for the nodes based on the graph topology; and computing, using a graph neural network, a congestion prediction for the circuit elements that are represented as nodes based on the extracted network embeddings and the extracted degree features.

    METHODS AND SYSTEMS FOR TRAINING A GRAPH NEURAL NETWORK USING SUPERVISED CONTRASTIVE LEARNING
    4.
    发明申请
    METHODS AND SYSTEMS FOR TRAINING A GRAPH NEURAL NETWORK USING SUPERVISED CONTRASTIVE LEARNING 有权

    公开(公告)号：US20220383127A1

    公开(公告)日：2022-12-01

    申请号：US17335904

    申请日：2021-06-01

    Applicant: Basmah ALTAF ,  Yingxue ZHANG

    Inventor： Basmah ALTAF ,  Yingxue ZHANG

    IPC: G06N3/08

    Abstract: Methods and systems are described for training a graph neural network (GNN) to perform a node classification task. A GNN is first pre-trained using ground-truth labeled nodes. The GNN is then used to predict labels for a set of unlabeled nodes, and the predicted labels having confidence indicators that satisfy a high confidence criterion are selected as pseudo labels that are assigned to corresponding nodes. The pseudo labeled nodes and ground-truth labeled nodes are combined together into a combined set of labeled nodes. Using the combined set of labeled nodes, the GNN is trained by computing a total loss between predicted labels generated by the GNN and assigned labels in the combined set of labeled nodes, the total loss being computed as a sum of a computed cross-entropy loss and a computed supervised contrastive loss.

    DYNAMIC GRAPH REPRESENTATION LEARNING WITH SELF-SUPERVISION
    5.
    发明公开
    DYNAMIC GRAPH REPRESENTATION LEARNING WITH SELF-SUPERVISION 审中-公开

    公开(公告)号：US20240119294A1

    公开(公告)日：2024-04-11

    申请号：US18477231

    申请日：2023-09-28

    Applicant: Mhd Ali ALOMRANI ,  Mahdi BIPARVA ,  Yingxue ZHANG

    Inventor： Mhd Ali ALOMRANI ,  Mahdi BIPARVA ,  Yingxue ZHANG

    IPC: G06N3/0895

    CPC classification number: G06N3/0895

    Abstract: System, method, and computer readable medium for dynamic graph representation learning with self-supervision, including extracting a time window of data from the dynamic graph representation to obtain a history graph that represents a sub-set of the dynamic graph representation; generating, using an encoder model configured by a set of learned encoder parameters and implemented by the computer system, a set of embeddings for the history graph; and predicting, using a first decoder model configured by a first set of learned decoder parameters and implemented by the computer system, one or more predictions for the dynamic graph representation corresponding to the specific prediction task.

    SYSTEM, METHOD, AND COMPUTER-READABLE MEDIA FOR LEAKAGE CORRECTION IN GRAPH NEURAL NETWORK BASED RECOMMENDER SYSTEMS
    6.
    发明申请
    SYSTEM, METHOD, AND COMPUTER-READABLE MEDIA FOR LEAKAGE CORRECTION IN GRAPH NEURAL NETWORK BASED RECOMMENDER SYSTEMS 有权

    公开(公告)号：US20220405588A1

    公开(公告)日：2022-12-22

    申请号：US17824556

    申请日：2022-05-25

    Applicant: Ishaan KUMAR ,  Yaochen HU ,  Yingxue ZHANG

    Inventor： Ishaan KUMAR ,  Yaochen HU ,  Yingxue ZHANG

    IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063

    Abstract: Systems, methods, and computer-readable media provide a graph processing system that incorporates a graph neural network (GNN) based recommender system (RS), as well as a method for training a GNN based RS to address feature leakage that leads to overfitting of the trained GNN based RS. A message correction algorithm is used to modify a user node embedding and a positive item node embedding generated by the graph neural network when generating mini batches of training triples used to train the GNN based RS. The GNN message passing operations are performed on one graph only, in contrast to existing approaches which typically run GNN message passing operations on multiple adjusted input graphs constructed for multiple training triples.

    RECOMMENDER SYSTEM USING BAYESIAN GRAPH CONVOLUTION NETWORKS
    9.
    发明申请
    RECOMMENDER SYSTEM USING BAYESIAN GRAPH CONVOLUTION NETWORKS 有权

    公开(公告)号：US20210248449A1

    公开(公告)日：2021-08-12

    申请号：US16789325

    申请日：2020-02-12

    Applicant: Jianing SUN ,  Yingxue ZHANG ,  Florence ROBERT-RÉGOL ,  Mark COATES

    Inventor： Jianing SUN ,  Yingxue ZHANG ,  Florence ROBERT-RÉGOL ,  Mark COATES

    IPC: G06N3/04 ,  G06N3/08 ,  G06F16/901 ,  G06F17/16 ,  G06F17/18

    Abstract: System and method for processing an observed bipartite graph that has a plurality of user nodes, a plurality of item nodes, and an observed graph topology that defines edges connecting at least some of the user nodes to some of the item nodes such that at least some nodes have node neighbourhoods comprising edge connections to one or more other nodes. A plurality of random graph topologies are derived that are realizations of the observed graph topology by replacing the node neighbourhoods of at least some nodes with the node neighbourhoods of other nodes. A non-linear function is trained using the plurality of user nodes, plurality of item nodes and plurality of random graph topologies to learn user node embeddings and item node embeddings for the plurality of user nodes and plurality of item nodes, respectively.

Patent Agency Ranking