公开(公告)号：US20220318307A1

公开(公告)日：2022-10-06

申请号：US17577187

申请日：2022-01-17

Applicant: Pinterest, Inc.

Inventor： Jurij Leskovec ,  Chantat Eksombatchai ,  Kaifeng Chen ,  Ruining He ,  Rex Ying

IPC: G06F16/901 ,  G06F16/906 ,  G06K9/62 ,  G06N20/00 ,  G06F16/22 ,  G06F16/9536 ,  G06F16/9535 ,  G06N3/04 ,  G06N3/08 ,  G06F16/182 ,  G06F16/9035 ,  G06F16/51 ,  G06V30/196

Abstract: Systems and methods for generating embeddings for nodes of a corpus graph are presented. More particularly, operations for generation of an aggregated embedding vector for a target node is efficiently divided among operations on a central processing unit and operations on a graphic processing unit. With regard to a target node within a corpus graph, processing by one or more central processing units (CPUs) is conducted to identify the target node's relevant neighborhood (of nodes) within the corpus graph. This information is prepared and passed to one or more graphic processing units (GPUs) that determines the aggregated embedding vector for the target node according to data of the relevant neighborhood of the target node.

公开(公告)号：US11409821B1

公开(公告)日：2022-08-09

申请号：US16909894

申请日：2020-06-23

Applicant: Pinterest, Inc.

Inventor： Aditya Pal ,  Chantat Eksombatchai ,  Yitong Zhou ,  Bo Zhao ,  Charles Joseph Rosenberg ,  Jurij Leskovec

IPC: G06F16/9535 ,  G06F16/906

Abstract: Systems and methods for recommending content to an online service subscriber are presented. For each subscriber, content items that were the subject of the subscriber's prior interactions are projected, via associated embedding vectors, into a content item embedding space. The content items, via their projections into the content item embedding space, are clustered to form a plurality of interest clusters for the subscriber. A representative embedding vector is determined for each interest cluster, and a plurality of these embedding vectors are stored as the representative embedding vectors for the subscriber. The online service, in response to a request for recommended content for a subscriber, selects a first representative embedding vector associated with the subscriber and identifies a new content item from a corpus of content items according to a similarity measure between the first representative embedding vector and an embedding vector associated with the new content item.

公开(公告)号：US11232152B2

公开(公告)日：2022-01-25

申请号：US16178443

申请日：2018-11-01

Applicant: Pinterest, Inc.

Inventor： Jurij Leskovec ,  Chantat Eksombatchai ,  Kaifeng Chen ,  Ruining He ,  Rex Ying

IPC: G06F16/901 ,  G06F16/906 ,  G06K9/62 ,  G06N20/00 ,  G06F16/22 ,  G06F16/9536 ,  G06F16/2453 ,  G06F16/9535 ,  G06N3/04 ,  G06N3/08 ,  G06F16/182 ,  G06F16/9035 ,  G06K9/68 ,  G06Q30/02 ,  G06N5/04 ,  G06F16/51 ,  G06F9/38 ,  G06N7/00

Abstract: Systems and methods for generating embeddings for nodes of a corpus graph are presented. More particularly, operations for generation of an aggregated embedding vector for a target node is efficiently divided among operations on a central processing unit and operations on a graphic processing unit. With regard to a target node within a corpus graph, processing by one or more central processing units (CPUs) is conducted to identify the target node's relevant neighborhood (of nodes) within the corpus graph. This information is prepared and passed to one or more graphic processing units (GPUs) that determines the aggregated embedding vector for the target node according to data of the relevant neighborhood of the target node.

公开(公告)号：US11227014B2

公开(公告)日：2022-01-18

申请号：US16273969

申请日：2019-02-12

Applicant: Pinterest, Inc.

Inventor： Jurij Leskovec ,  Chantat Eksombatchai ,  Kaifeng Chen ,  Ruining He ,  Rex Ying

IPC: G06F16/901 ,  G06F16/906 ,  G06K9/62 ,  G06F16/9536 ,  G06F16/9535 ,  G06N3/04 ,  G06K9/68 ,  G06F16/51 ,  G06N20/00 ,  G06F16/22 ,  G06N3/08 ,  G06F16/182 ,  G06F16/9035 ,  G06F9/38

Abstract: Systems and methods for generating embeddings for nodes of a corpus graph are presented. More particularly, embedding information of a target node may be based on the node itself, as well as related, relevant nodes to the target node within a corpus graph. The information of various nodes among the relevant nodes to the target node can be used to weight or influence the embedding information. Disclosed systems and methods include generating neighborhood embedding information for a target node, where the neighborhood embedding information includes embedding information from neighborhood nodes of the target node's relevant neighborhood, and where certain nodes having more relevance to the target node can be weighted to influence the generation of the neighborhood embedding information over nodes having less relevance to the target node.

公开(公告)号：US20190286752A1

公开(公告)日：2019-09-19

申请号：US16101184

申请日：2018-08-10

Applicant: Pinterest, Inc.

Inventor： Jurij Leskovec ,  Chantat Eksombatchai ,  Ruining He ,  Kaifeng Chen ,  Rex Ying

IPC: G06F17/30 ,  G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: Systems and methods for generating embeddings for nodes of a corpus graph are presented. The embeddings correspond to aggregated embedding vectors for nodes of the corpus graph. Without processing the entire corpus graph to generate all aggregated embedding vectors, a relevant neighborhood of nodes within the corpus graph are identified for a target node of the corpus graph. Based on embedding information of the target node's immediate neighbors, and also upon neighborhood embedding information from the target node's relevant neighborhood, an aggregated embedding vector can be generated for the target node that comprises both an embedding vector portion corresponding to the target node, as well as a neighborhood embedding vector portion, corresponding to embedding information of the relevant neighborhood of the target node. Utilizing both portions of the aggregated embedding vector leads to improved content recommendation to a user in response to a query.