Patents by Inventor Guoqing Zheng

Guoqing Zheng has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Joint learning from explicit and inferred labels
    Patent number: 12073326
    Abstract: This document relates to training of machine learning models. One example method involves providing a machine learning model having a first classification layer, a second classification layer, and an encoder that feeds into the first classification layer and the second classification layer. The example method also involves obtaining first training examples having explicit labels and second training examples having inferred labels. The inferred labels are based at least on actions associated with the second training examples. The example method also involves training the machine learning model using the first training examples and the second training examples using a training objective that considers first training loss of the first classification layer for the explicit labels and second training loss of the second classification layer for the inferred labels. The method also involves outputting a trained machine learning model having the encoder and the first classification layer.
    Type: Grant
    Filed: October 4, 2023
    Date of Patent: August 27, 2024
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Subhabrata Mukherjee, Guoqing Zheng, Ahmed Awadalla, Milad Shokouhi, Susan Theresa Dumais, Kai Shu
  • JOINT LEARNING FROM EXPLICIT AND INFERRED LABELS
    Publication number: 20240046087
    Abstract: This document relates to training of machine learning models. One example method involves providing a machine learning model having a first classification layer, a second classification layer, and an encoder that feeds into the first classification layer and the second classification layer. The example method also involves obtaining first training examples having explicit labels and second training examples having inferred labels. The inferred labels are based at least on actions associated with the second training examples. The example method also involves training the machine learning model using the first training examples and the second training examples using a training objective that considers first training loss of the first classification layer for the explicit labels and second training loss of the second classification layer for the inferred labels. The method also involves outputting a trained machine learning model having the encoder and the first classification layer.
    Type: Application
    Filed: October 4, 2023
    Publication date: February 8, 2024
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Subhabrata Mukherjee, Guoqing Zheng, Ahmed Awadalla, Milad Shokouhi, Susan Theresa Dumais, Kai Shu
  • Joint learning from explicit and inferred labels
    Patent number: 11816566
    Abstract: This document relates to training of machine learning models. One example method involves providing a machine learning model having a first classification layer, a second classification layer, and an encoder that feeds into the first classification layer and the second classification layer. The example method also involves obtaining first training examples having explicit labels and second training examples having inferred labels. The inferred labels are based at least on actions associated with the second training examples. The example method also involves training the machine learning model using the first training examples and the second training examples using a training objective that considers first training loss of the first classification layer for the explicit labels and second training loss of the second classification layer for the inferred labels. The method also involves outputting a trained machine learning model having the encoder and the first classification layer.
    Type: Grant
    Filed: May 18, 2020
    Date of Patent: November 14, 2023
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Subhabrata Mukherjee, Guoqing Zheng, Ahmed Awadalla, Milad Shokouhi, Susan Theresa Dumais, Kai Shu
  • JOINT LEARNING FROM EXPLICIT AND INFERRED LABELS
    Publication number: 20210357747
    Abstract: This document relates to training of machine learning models. One example method involves providing a machine learning model having a first classification layer, a second classification layer, and an encoder that feeds into the first classification layer and the second classification layer. The example method also involves obtaining first training examples having explicit labels and second training examples having inferred labels. The inferred labels are based at least on actions associated with the second training examples. The example method also involves training the machine learning model using the first training examples and the second training examples using a training objective that considers first training loss of the first classification layer for the explicit labels and second training loss of the second classification layer for the inferred labels. The method also involves outputting a trained machine learning model having the encoder and the first classification layer.
    Type: Application
    Filed: May 18, 2020
    Publication date: November 18, 2021
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Subhabrata Mukherjee, Guoqing Zheng, Ahmed Awadalla, Milad Shokouhi, Susan Theresa Dumais, Kai Shu