公开(公告)号：US20250117635A1

公开(公告)日：2025-04-10

申请号：US18987305

申请日：2024-12-19

Applicant: Visa International Service Association

Inventor： Jiarui Sun ,  Mengting Gu ,  Michael Yeh ,  Liang Wang ,  Wei Zhang

IPC: G06N3/049 ,  G06F17/16

Abstract: Described are a system, method, and computer program product for dynamic node classification in temporal-based machine learning classification models. The method includes receiving graph data of a discrete time dynamic graph including graph snapshots, and node classifications associated with all nodes in the discrete time dynamic graph. The method includes converting the discrete time dynamic graph to a time-augmented spatio-temporal graph and generating an adjacency matrix based on a temporal walk of the time-augmented spatio-temporal graph. The method includes generating an adaptive information transition matrix based on the adjacency matrix and determining feature vectors based on the nodes and the node attribute matrix of each graph snapshot. The method includes generating and propagating initial node representations across information propagation layers using the adaptive information transition matrix and classifying a node of the discrete time dynamic graph subsequent to the first time period based on final node representations.

公开(公告)号：US12253991B2

公开(公告)日：2025-03-18

申请号：US18280828

申请日：2022-06-09

Applicant: Visa International Service Association

Inventor： Yan Zheng ,  Wei Zhang ,  Michael Yeh ,  Liang Wang ,  Junpeng Wang ,  Shubham Jain ,  Zhongfang Zhuang

IPC: G06F16/00 ,  G06F16/22

Abstract: Provided is a system for analyzing features associated with entities using an embedding tree, the system including at least one processor programmed or configured to receive a dataset associated with a plurality of entities, wherein the dataset comprises a plurality of data instances for a plurality of entities. The processor may be programmed or configured to generate at least two embeddings based on the dataset and determine split criteria for partitioning an embedding space of at least one embedding tree associated with the dataset based on feature data associated with an entity and embedding data associated with the at least two embeddings. The processor may be programmed or configured to generate at least one embedding tree having a plurality of nodes based on the split criteria. Methods and computer program products are also provided.

公开(公告)号：US20240403715A1

公开(公告)日：2024-12-05

申请号：US18694152

申请日：2021-09-22

Applicant: Visa International Service Association

Inventor： Liang Wang ,  Junpeng Wang ,  Yan Zheng ,  Shubham Jain ,  Michael Yeh ,  Zhongfang Zhuang ,  Wei Zhang ,  Hao Yang

IPC: G06N20/00 ,  G06N5/022

Abstract: Systems, methods, and computer program products that obtain a plurality of features associated with a plurality of samples and a plurality of labels for the plurality of samples; generate a plurality of first predictions for the plurality of samples with a first machine learning model; generate a plurality of second predictions for the plurality of samples with a second machine learning model; generate, based on the plurality of first predictions, the plurality of second predictions, the plurality of labels, and a plurality of groups of samples of the plurality of samples; determine, based on the plurality of groups of samples, a first success rate associated with the first machine learning model and a second success rate associated with the second machine learning model; and identify, based on the first success rate and the second success rate, a weak point in the machine learning first model or the second model.

公开(公告)号：US20240256863A1

公开(公告)日：2024-08-01

申请号：US18426717

申请日：2024-01-30

Applicant: Visa International Service Association

Inventor： Huiyuan Chen ,  Mahashweta Das ,  Michael Yeh ,  Yujie Fan ,  Yan Zheng ,  Junpeng Wang ,  Vivian Wan Yin Lai ,  Hao Yang

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and computer program products are provided for optimizing training loss of a graph neural network machine learning model using bi-level optimization. An example method includes receiving a training dataset comprising graph data associated with a graph, training a graph neural network (GNN) machine learning model using a loss equation according to a bi-level optimization problem and based on the training dataset, where training the GNN machine learning model using the loss equation according to the bi-level optimization problem includes determining a solution to an inner loss problem and a solution to an outer loss problem, and providing a trained GNN machine learning model based on training the GNN machine learning model.

公开(公告)号：US20240152499A1

公开(公告)日：2024-05-09

申请号：US18280828

申请日：2022-06-09

Applicant: Visa International Service Association

Inventor： Yan Zheng ,  Wei Zhang ,  Michael Yeh ,  Liang Wang ,  Junpeng Wang ,  Shubham Jain ,  Zhongfang Zhuang

IPC: G06F16/22

CPC classification number: G06F16/2246

Abstract: Provided is a system for analyzing features associated with entities using an embedding tree, the system including at least one processor programmed or configured to receive a dataset associated with a plurality of entities, wherein the dataset comprises a plurality of data instances for a plurality of entities. The processor may be programmed or configured to generate at least two embeddings based on the dataset and determine split criteria for partitioning an embedding space of at least one embedding tree associated with the dataset based on feature data associated with an entity and embedding data associated with the at least two embeddings. The processor may be programmed or configured to generate at least one embedding tree having a plurality of nodes based on the split criteria. Methods and computer program products are also provided.

公开(公告)号：US11861324B2

公开(公告)日：2024-01-02

申请号：US18006649

申请日：2022-05-25

Applicant: Visa International Service Association

Inventor： Yan Zheng ,  Michael Yeh ,  Junpeng Wang ,  Wei Zhang ,  Liang Wang ,  Hao Yang ,  Prince Osei Aboagye

IPC: G06F5/01 ,  G06F40/40 ,  G06F17/16

CPC classification number: G06F5/01 ,  G06F17/16 ,  G06F40/40

Abstract: Provided is a method for normalizing embeddings for cross-embedding alignment. The method may include applying mean centering to the at least one embedding set, applying spectral normalization to the at least one embedding set, and/or applying length normalization to the at least one embedding set. Spectral normalization may include decomposing the at least one embedding set, determining an average singular value of the at least one embedding set, determining a respective substitute singular value for each respective singular value of a diagonal matrix, and/or replacing the at least one embedding set with a product of the at least one embedding set, a right singular vector, and an inverse of the substitute diagonal matrix. The mean centering, spectral normalization, and/or length normalization may be iteratively repeated for a configurable number of iterations. A system and computer program product are also disclosed.

公开(公告)号：US11836159B2

公开(公告)日：2023-12-05

申请号：US17066852

申请日：2020-10-09

Applicant: Visa International Service Association

Inventor： Michael Yeh ,  Liang Gou ,  Wei Zhang ,  Dhruv Gelda ,  Zhongfang Zhuang ,  Yan Zheng

IPC: G06F16/28 ,  G06N3/08 ,  G06F16/23

CPC classification number: G06F16/284 ,  G06F16/2379 ,  G06N3/08

Abstract: Provided are systems for analyzing a relational database using embedding learning that may include at least one processor programmed or configured to generate one or more entity-relation matrices from a relational database and perform, for each entity-relation matrix of the one or more entity-relation matrices, an embedding learning process on an embedding associated with an entity. When performing the embedding learning process on the embedding associated with the entity, the at least one processor is programmed or configured to generate an updated embedding associated with the entity. Computer implemented methods and computer-program products are also provided.

公开(公告)号：US20230252557A1

公开(公告)日：2023-08-10

申请号：US18013350

申请日：2021-06-22

Applicant: Visa International Service Association

Inventor： Zhongfang Zhuang ,  Michael Yeh ,  Wei Zhang ,  Javid Ebrahimi

IPC: G06Q40/00

CPC classification number: G06Q40/00

Abstract: Systems, methods, and computer program products train a residual neural network including a first fully connected layer, a first recurrent neural network layer, and at least one skip connection for anomaly detection. The at least one skip connection directly connects at least one of (i) an output of the first fully connected layer to a first other layer downstream of the first recurrent neural network layer in the residual neural network and (ii) an output of the first recurrent neural network layer to a second other layer downstream of a second recurrent neural network layer in the residual neural network.

公开(公告)号：US20220407879A1

公开(公告)日：2022-12-22

申请号：US17763282

申请日：2021-10-18

Applicant: Visa International Service Association

Inventor： Bo Dong ,  Yuhang Wu ,  Yu-San Lin ,  Michael Yeh ,  Hao Yang

IPC: H04L9/40

Abstract: Described are a system, method, and computer program product for user network activity anomaly detection. The method includes receiving network resource data associated with network resource activity of a plurality of users and generating a plurality of layers of a multilayer graph from the network resource data. Each layer of the plurality of layers may include a plurality of nodes, which are associated with users, connected by a plurality of edges, which are representative of node interdependency. The method also includes generating a plurality of adjacency matrices from the plurality of layers and generating a merged single layer graph based on a weighted sum of the plurality of adjacency matrices. The method further includes generating anomaly scores for each node in the merged single layer graph and determining a set of anomalous users based on the anomaly scores.