-
Patent Agency Ranking
公开(公告)号：US20200372355A1
公开(公告)日：2020-11-26
申请号：US16883209
申请日：2020-05-26
Applicant: Google LLC
Inventor： Daniel S. Tarlow , Matej Balog , Bart van Merrienboer , Yujia Li , Subhodeep Moitra
Abstract: A computer-implemented method for computing node embeddings of a sparse graph that is an input of a sparse graph neural network is described. Each node embedding corresponds to a respective node of the sparse graph and represents feature information of the respective node and a plurality of neighboring nodes of the respective node. The method includes: receiving an adjacency matrix that represents edges of the sparse graph; receiving a weight matrix representing, for each node of the sparse graph, a level of influence of respective neighboring nodes on the node; initializing, for each node of the sparse graph, a respective node embedding; transforming the adjacency matrix into a low-bandwidth adjacency matrix, and performing the following operations at least once: generating a message propagation matrix as a product of the low-bandwidth adjacency matrix, the node embeddings of the nodes, and the weight matrix, wherein the message propagation matrix represents message propagation among the nodes of the sparse graph, and updating the node embeddings of the sparse graph by processing the message propagation matrix and the node embeddings of the nodes using an encoder neural network of the sparse graph neural network.
-
公开(公告)号：US20250118401A1
公开(公告)日：2025-04-10
申请号：US17143083
申请日：2021-01-06
Applicant: Google LLC
Inventor： Edward Choi , Andrew M. Dai , Gerardo Flores , Yuan Xue , Michael Ward Dusenberry , Zhen Xu , Yujia Li
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing data about a medical encounter using neural networks. One of the methods includes obtaining features for a medical encounter associated with the patient, each feature representing a corresponding health event associated with the medical encounter and each of the plurality of features belonging to a vocabulary of possible features that each represent a different health event; and generating respective final embeddings for each of the features for the medical encounter by applying a sequence of one or more self-attention blocks to the features for the medical encounter, wherein each of the one or more self-attention blocks receives a respective block input for each of the features and applies self-attention over the block inputs to generate a respective block output for each of the features.
-
公开(公告)号：US11947503B2
公开(公告)日：2024-04-02
申请号：US17351086
申请日：2021-06-17
Applicant: Google LLC
Inventor： Hanjun Dai , Azade Nazi , Yujia Li , Bo Dai , Dale Eric Schuurmans
CPC classification number: G06F16/212 , G06F16/2237 , G06F16/2246 , G06N3/045
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating data defining a graph. In one aspect, a method comprises: sequentially generating a respective edge set for each node in the graph, wherein for each of a plurality of nodes after a first node, generating the edge set for the node comprises: receiving a context embedding for the node that summarizes a respective edge set for each node that precedes the node; generating, based on the context embedding for the node: (i) a respective edge set for the node, and (ii) a respective embedding of the edge set for the node; generating a context embedding for a next node in the ordering of the nodes using the embedding of the edge set for the node; and adding the set of edges defined by the edge set for the node to the graph.
-
公开(公告)号：US11562239B2
公开(公告)日：2023-01-24
申请号：US16883209
申请日：2020-05-26
Applicant: Google LLC
Inventor： Daniel S. Tarlow , Matej Balog , Bart van Merrienboer , Yujia Li , Subhodeep Moitra
Abstract: A computer-implemented method for computing node embeddings of a sparse graph that is an input of a sparse graph neural network is described. Each node embedding corresponds to a respective node of the sparse graph and represents feature information of the respective node and a plurality of neighboring nodes of the respective node. The method includes: receiving an adjacency matrix that represents edges of the sparse graph; receiving a weight matrix representing, for each node of the sparse graph, a level of influence of respective neighboring nodes on the node; initializing, for each node of the sparse graph, a respective node embedding; transforming the adjacency matrix into a low-bandwidth adjacency matrix, and performing the following operations at least once: generating a message propagation matrix as a product of the low-bandwidth adjacency matrix, the node embeddings of the nodes, and the weight matrix, wherein the message propagation matrix represents message propagation among the nodes of the sparse graph, and updating the node embeddings of the sparse graph by processing the message propagation matrix and the node embeddings of the nodes using an encoder neural network of the sparse graph neural network.
-
公开(公告)号：US20220414067A1
公开(公告)日：2022-12-29
申请号：US17351086
申请日：2021-06-17
Applicant: Google LLC
Inventor： Hanjun Dai , Azade Nazi , Yujia Li , Bo Dai , Dale Eric Schuurmans
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating data defining a graph. In one aspect, a method comprises: sequentially generating a respective edge set for each node in the graph, wherein for each of a plurality of nodes after a first node, generating the edge set for the node comprises: receiving a context embedding for the node that summarizes a respective edge set for each node that precedes the node; generating, based on the context embedding for the node: (i) a respective edge set for the node, and (ii) a respective embedding of the edge set for the node; generating a context embedding for a next node in the ordering of the nodes using the embedding of the edge set for the node; and adding the set of edges defined by the edge set for the node to the graph.
-
-
-
-
Search Results
5
records
(took 0.022 seconds)
