公开(公告)号：US20250021886A1

公开(公告)日：2025-01-16

申请号：US18896306

申请日：2024-09-25

Applicant: Visa International Service Association

Inventor： Kwei-Herng Lai ,  Lan Wang ,  Huiyuan Chen ,  Mangesh Bendre ,  Mahashweta Das ,  Hao Yang

IPC: G06N20/00 ,  G06F18/2413

Abstract: Methods, systems, and computer program products may formulate an iterative data mix up problem into a Markov decision process (MDP) with a tailored reward signal to guide a learning process. To solve the MDP, a deep deterministic actor-critic framework may be modified to adapt a discrete-continuous decision space for training a data augmentation policy.

公开(公告)号：US11841856B2

公开(公告)日：2023-12-12

申请号：US17907996

申请日：2022-03-24

Applicant: Visa International Service Association

Inventor： Mangesh Bendre ,  Robert Brian Christensen ,  Yan Zheng ,  Wei Zhang ,  Fei Wang ,  Hao Yang

IPC: G06F16/00 ,  G06F16/2453 ,  G06F16/27 ,  G06F16/2458 ,  G06F7/08

CPC classification number: G06F16/24537 ,  G06F7/08 ,  G06F16/2477 ,  G06F16/27

Abstract: Described are a system, method, and computer program product for efficiently joining time-series data tables. The method includes loading a first table and a second table into a memory and generating a set of first key-value pairs based on a set of first time-series records and a set of second key-value pairs based on a set of second time-series records. The method also includes sorting the set of first key-value pairs and the set of second key-value pairs. The method further includes interleaving the set of first key-value pairs with the set of second key-value pairs and sequentially matching the sets of time-series records to form a joined table. The method further includes, in response to matching each respective second time-series record with the respective first time-series record, removing the respective second time-series record from the at least one memory.

公开(公告)号：US20230196198A1

公开(公告)日：2023-06-22

申请号：US18015976

申请日：2022-05-24

Applicant: Visa International Service Association

Inventor： Mangesh Bendre ,  Mahashweta Das ,  Fei Wang ,  Hao Yang

IPC: G06N20/00 ,  G06N5/022

CPC classification number: G06N20/00 ,  G06N5/022

Abstract: Provided are systems, methods, and computer program products for generating node embeddings. The system includes at least one processor programmed or configured to generate a graph comprising a plurality of nodes, generate an embedding for each node of the plurality of nodes, each embedding comprising at least one polar angle and a vector length. store each embedding of a plurality of embeddings in memory, and in response to processing the graph with a machine-learning algorithm, convert at least one embedding of the plurality of embeddings to Cartesian coordinates.

公开(公告)号：US20220114456A1

公开(公告)日：2022-04-14

申请号：US17495214

申请日：2021-10-06

Applicant: Visa International Service Association

Inventor： Azita Nouri ,  Mangesh Bendre ,  Mahashweta Das ,  Fei Wang ,  Hao Yang ,  Adit Krishnan

IPC: G06N5/02 ,  G06N5/04 ,  G06K9/62 ,  G06F9/38

Abstract: Methods, systems, and computer program products for knowledge graph based embedding, explainability, and/or multi-task learning may connect task-specific inductive models with knowledge graph completion and enrichment processes.

公开(公告)号：US12242939B2

公开(公告)日：2025-03-04

申请号：US18686563

申请日：2023-08-04

Applicant: Visa International Service Association

Inventor： Kwei-Herng Lai ,  Lan Wang ,  Huiyuan Chen ,  Mangesh Bendre ,  Mahashweta Das ,  Hao Yang

IPC: G06N20/00 ,  G06F18/2413

Abstract: Methods, systems, and computer program products may formulate an iterative data mix up problem into a Markov decision process (MDP) with a tailored reward signal to guide a learning process. To solve the MDP, a deep deterministic actor-critic framework may be modified to adapt a discrete-continuous decision space for training a data augmentation policy.

公开(公告)号：US12198026B2

公开(公告)日：2025-01-14

申请号：US18015976

申请日：2022-05-24

Applicant: Visa International Service Association

Inventor： Mangesh Bendre ,  Mahashweta Das ,  Fei Wang ,  Hao Yang

IPC: G06N20/00 ,  G06N5/022

Abstract: Provided are systems, methods, and computer program products for generating node embeddings. The system includes at least one processor programmed or configured to generate a graph comprising a plurality of nodes, generate an embedding for each node of the plurality of nodes, each embedding comprising at least one polar angle and a vector length, store each embedding of a plurality of embeddings in memory, and in response to processing the graph with a machine-learning algorithm, convert at least one embedding of the plurality of embeddings to Cartesian coordinates.

公开(公告)号：US20240281718A1

公开(公告)日：2024-08-22

申请号：US18686563

申请日：2023-08-04

Applicant: VISA INTERNATIONAL SERVICE ASSOCIATION

Inventor： Kwei-Herng Lai ,  Lan Wang ,  Huiyuan Chen ,  Mangesh Bendre ,  Mahashweta Das ,  Hao Yang

IPC: G06N20/00 ,  G06F18/2413

CPC classification number: G06N20/00 ,  G06F18/24147

Abstract: Methods, systems, and computer program products may formulate an iterative data mix up problem into a Markov decision process (MDP) with a tailored reward signal to guide a learning process. To solve the MDP, a deep deterministic actor-critic framework may be modified to adapt a discrete-continuous decision space for training a data augmentation policy.

公开(公告)号：US20230306024A1

公开(公告)日：2023-09-28

申请号：US17907996

申请日：2022-03-24

Applicant: Visa International Service Association

Inventor： Mangesh Bendre ,  Robert Brian Christensen ,  Yan Zheng ,  Wei Zhang ,  Fei Wang ,  Hao Yang

IPC: G06F16/2453 ,  G06F7/08 ,  G06F16/2458 ,  G06F16/27

CPC classification number: G06F16/24537 ,  G06F7/08 ,  G06F16/2477 ,  G06F16/27

Abstract: Described are a system, method, and computer program product for efficiently joining time-series data tables. The method includes loading a first table and a second table into a memory and generating a set of first key-value pairs based on a set of first time-series records and a set of second key-value pairs based on a set of second time-series records. The method also includes sorting the set of first key-value pairs and the set of second key-value pairs. The method further includes interleaving the set of first key-value pairs with the set of second key-value pairs and sequentially matching the sets of time-series records to form a joined table. The method further includes, in response to matching each respective second time-series record with the respective first time-series record, removing the respective second time-series record from the at least one memory.