Patents by Inventor Tao B. Schardl

Tao B. Schardl 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).

  • Evolving graph convolutional networks for dynamic graphs
    Patent number: 11537852
    Abstract: A system includes a plurality of graph convolutional networks corresponding to a plurality of time steps, each network modelling a graph including nodes and edges, and in turn including a plurality of graph convolution units; an evolving mechanism; and an output layer. Each of the units, for a given one of the time steps, takes as input a graph adjacency matrix, a node feature matrix, and a parameter matrix for a current layer, and outputs a new node feature matrix for a next highest layer. The mechanism takes as input a parameter matrix for a prior time step updates the input parameter matrix, and outputs the parameter matrix for the given time step. The output layer obtains, as input, output of each of the units for a final time step, and based on the output of each of the units for the final time step, outputs a graph solution.
    Type: Grant
    Filed: February 13, 2020
    Date of Patent: December 27, 2022
    Assignees: International Business Machines Corporation, Massachusetts Institute of Technology
    Inventors: Jie Chen, Aldo Pareja, Giacomo Domeniconi, Tengfei Ma, Toyotaro Suzumura, Timothy Kaler, Tao B. Schardl, Charles E. Leiserson
  • EVOLVING GRAPH CONVOLUTIONAL NETWORKS FOR DYNAMIC GRAPHS
    Publication number: 20210256355
    Abstract: A system includes a plurality of graph convolutional networks corresponding to a plurality of time steps, each network modelling a graph including nodes and edges, and in turn including a plurality of graph convolution units; an evolving mechanism; and an output layer. Each of the units, for a given one of the time steps, takes as input a graph adjacency matrix, a node feature matrix, and a parameter matrix for a current layer, and outputs a new node feature matrix for a next highest layer. The mechanism takes as input a parameter matrix for a prior time step updates the input parameter matrix, and outputs the parameter matrix for the given time step. The output layer obtains, as input, output of each of the units for a final time step, and based on the output of each of the units for the final time step, outputs a graph solution.
    Type: Application
    Filed: February 13, 2020
    Publication date: August 19, 2021
    Inventors: Jie Chen, Aldo Pareja, Giacomo Domeniconi, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Timothy Kaler, Tao B. Schardl, Charles E. Leiserson