公开(公告)号：US20190073580A1

公开(公告)日：2019-03-07

申请号：US15694660

申请日：2017-09-01

Applicant: Facebook, Inc.

Inventor： Dmytro Dzhulgakov ,  Andrey Malevich

IPC: G06N3/04 ,  G06N3/08

Abstract: A computer system is optimized for implementing a neural network nodal graph that has dense inputs and sparse inputs. The computer system has a local machine that receives user inputs and is optimized for computing power, and has a remote machine that stores embedding matrices and parameters, and is optimized for memory capacity. In accordance with a cost function applied to each node, the neural network nodal graph is divided into graph segments based on its types of inputs and needed computing resources for execution. In accordance with the cost functions, the graph segments are divided between the remote and local machines for execution, and the results of all the graph segments are combined in the local machine.

公开(公告)号：US10083465B2

公开(公告)日：2018-09-25

申请号：US14019794

申请日：2013-09-06

Applicant: Facebook, Inc.

Inventor： Uladzimir Pashkevich ,  Andrew John Tulloch ,  Dmytro Dzhulgakov ,  Lars Seren Backstrom

IPC: G06F17/30 ,  G06Q30/02 ,  H04W4/21 ,  H04W4/20

CPC classification number: G06Q30/0275 ,  H04W4/21

Abstract: When an online system receives a request to present content items to a user, a content selection system included in the online system selects content items for presentation to the user during a latency period from the time the request was received until the time when the content items are sent. A feedback control mechanism communicates with each computing device of the content selection system to determine the latency period of each computing device. The feedback control mechanism also determines a target latency period in which content items are selected. By comparing the latency period of each computing device to the target latency period, an amount of information to be evaluated by each computing device is determined based on whether a computing device's latency period is greater than or less than the target latency period.

公开(公告)号：US10229357B2

公开(公告)日：2019-03-12

申请号：US14851336

申请日：2015-09-11

Applicant: Facebook, Inc.

Inventor： Ou Jin ,  Stuart Michael Bowers ,  Dmytro Dzhulgakov

IPC: G06N3/08 ,  G06N99/00

Abstract: The present disclosure is directed to a high-capacity training and prediction machine learning platform that can support high-capacity parameter models (e.g., with 10 billion weights). The platform implements a generic feature transformation layer for joint updating and a distributed training framework utilizing shard servers to increase training speed for the high-capacity model size. The models generated by the platform can be utilized in conjunction with existing dense baseline models to predict compatibilities between different groupings of objects (e.g., a group of two objects, three objects, etc.).

公开(公告)号：US20170076198A1

公开(公告)日：2017-03-16

申请号：US14851336

申请日：2015-09-11

Applicant: Facebook, Inc.

Inventor： Ou Jin ,  Stuart Michael Bowers ,  Dmytro Dzhulgakov

IPC: G06N3/08 ,  G06N99/00

CPC classification number: G06N99/005

Abstract: The present disclosure is directed to a high-capacity training and prediction machine learning platform that can support high-capacity parameter models (e.g., with 10 billion weights). The platform implements a generic feature transformation layer for joint updating and a distributed training framework utilizing shard servers to increase training speed for the high-capacity model size. The models generated by the platform can be utilized in conjunction with existing dense baseline models to predict compatibilities between different groupings of objects (e.g., a group of two objects, three objects, etc.).

Abstract translation: 本公开涉及可以支持大容量参数模型（例如，具有100亿个权重）的高容量训练和预测机器学习平台。 该平台实现了联合更新的通用特征转换层和利用碎片服务器的分布式培训框架，以提高高容量模型大小的培训速度。 由平台生成的模型可以与现有的密集基线模型一起使用，以预测不同对象组之间的兼容性（例如，一组两个对象，三个对象等）。

公开(公告)号：US20150073920A1

公开(公告)日：2015-03-12

申请号：US14019794

申请日：2013-09-06

Applicant: Facebook, Inc.

Inventor： Uladzimir Pashkevich ,  Andrew John Tulloch ,  Dmytro Dzhulgakov ,  Lars Seren Backstrom

IPC: H04L29/08 ,  G06Q30/02

CPC classification number: G06Q30/0275 ,  H04W4/21

Abstract: When an online system receives a request to present content items to a user, a content selection system included in the online system selects content items for presentation to the user during a latency period from the time the request was received until the time when the content items are sent. A feedback control mechanism communicates with each computing device of the content selection system to determine the latency period of each computing device. The feedback control mechanism also determines a target latency period in which content items are selected. By comparing the latency period of each computing device to the target latency period, an amount of information to be evaluated by each computing device is determined based on whether a computing device's latency period is greater than or less than the target latency period.

Abstract translation: 当在线系统接收到向用户呈现内容项目的请求时，包括在在线系统中的内容选择系统在从接收请求的时间到内容项目的时间期间的等待期间内选择用于呈现给用户的内容项目 被发送。 反馈控制机构与内容选择系统的每个计算设备进行通信，以确定每个计算设备的等待时间。 反馈控制机构还确定选择内容项的目标等待时间周期。 通过将每个计算设备的等待时间间隔与目标等待时间进行比较，基于计算设备的等待时间周期是否大于或小于目标等待时间周期来确定由每个计算设备评估的信息量。