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：US20170017886A1

公开(公告)日：2017-01-19

申请号：US14799517

申请日：2015-07-14

Applicant: Facebook, Inc.

Inventor： Tianshi Gao ,  Shyamsundar Rajaram ,  Stuart Michael Bowers

IPC: G06N5/04 ,  G06F17/30 ,  G06N99/00

CPC classification number: G06N5/04 ,  G06N99/005 ,  G06Q30/02 ,  G06Q30/0241 ,  G06Q50/01

Abstract: Some embodiments include a method of generating a compatibility score for a grouping of objects based on correlations between attributes of the objects. An example grouping is a pair of user and ad. The method may be implemented using a multi-threaded pipeline architecture that utilizes a learning model to compute the compatibility score. The learning model determines correlations between a first object's attributes (e.g., user's liked pages, user demographics, user's apps installed, pixels visited, etc.) and a second object's attributes (e.g., expressed or implied). Example expressed attributes can be targeting keywords; example implied attributes can be object IDs associated with the ad.

Abstract translation: 一些实施例包括基于对象的属性之间的相关性来生成对象分组的兼容性分数的方法。 示例分组是一对用户和广告。 该方法可以使用利用学习模型来计算兼容性分数的多线程流水线架构来实现。 学习模型确定第一对象的属性（例如，用户喜爱的页面，用户人口统计，安装的用户的应用，被访问的像素等）与第二对象的属性（例如，表示或暗示的）之间的相关性。 示例表示的属性可以是定位关键字; 示例隐含的属性可以是与广告相关联的对象ID。

公开(公告)号：US20160358103A1

公开(公告)日：2016-12-08

申请号：US14732513

申请日：2015-06-05

Applicant: Facebook, Inc.

Inventor： Stuart Michael Bowers ,  Hussein Mohamed Hassan Mehanna ,  Alisson Gusatti Azzolini ,  Jeffrey Scott Dunn ,  Rodrigo Bouchardet Farnham ,  James Robert Paton ,  Aleksandr Sidorov ,  Pamela Shen Vagata ,  Xiaowen Xie

IPC: G06N99/00

CPC classification number: G06N20/00 ,  G06F9/4881 ,  G06N3/12

Abstract: Some embodiments include a method of machine learner workflow processing. For example, a workflow execution engine can receive an interdependency graph of operator instances for a workflow run. The operator instances can be associated with one or more operator types. The workflow execution engine can assign one or more computing environments from a candidate pool to execute the operator instances based on the interdependency graph. The workflow execution engine can generate a schedule plan of one or more execution requests associated with the operator instances. The workflow execution engine can distribute code packages associated the operator instances to the assigned computing environments. The workflow execution engine can maintain a memoization repository to cache one or more outputs of the operator instances upon completion of the execution requests.

Abstract translation: 一些实施例包括机器学习者工作流程处理的方法。 例如，工作流执行引擎可以接收工作流运行的操作员实例的相互依赖关系图。 运营商实例可以与一个或多个运营商类型相关联。 工作流执行引擎可以从候选池分配一个或多个计算环境，以基于相互依赖图来执行运算符实例。 工作流执行引擎可以生成与操作者实例相关联的一个或多个执行请求的调度计划。 工作流执行引擎可以将与操作员实例关联的代码包分发到分配的计算环境。 完成执行请求后，工作流执行引擎可以维护一个记忆库，以缓存操作符实例的一个或多个输出。

公开(公告)号：US10438235B2

公开(公告)日：2019-10-08

申请号：US14160342

申请日：2014-01-21

Applicant: Facebook, Inc.

Inventor： Andrew John Tulloch ,  Stuart Michael Bowers ,  Joaquin Ignacio Quinonero Candela

IPC: G06Q30/00 ,  G06Q30/02 ,  G06Q50/00

Abstract: An advertising system has limited computing resources to spend evaluating advertisements of advertisers to determine a “best” advertisement to serve to users of a social networking system. The computing resources are allocated (e.g., by varying the number of advertisements that are considered for presentation to a user) based on the neediness of the user and/or the advertiser on a per impression basis. The neediness of a user may be determined by grouping users into groups and determining a yield curve of expected revenue per computing resource used. Then, the revenue may be maximized across impression opportunities for multiple users. The neediness of an advertiser may be determined by biasing the selection of one advertiser's advertisements over another advertiser's advertisements based on an expected revenue, an expected number of interactions of the advertisement, or otherwise maximizing a satisfaction coefficient for the advertiser.

公开(公告)号：US10395181B2

公开(公告)日：2019-08-27

申请号：US14732513

申请日：2015-06-05

Applicant: Facebook, Inc.

Inventor： Stuart Michael Bowers ,  Hussein Mohamed Hassan Mehanna ,  Alisson Gusatti Azzolini ,  Jeffrey Scott Dunn ,  Rodrigo Bouchardet Farnham ,  James Robert Paton ,  Aleksandr Sidorov ,  Pamela Shen Vagata ,  Xiaowen Xie

IPC: G06N3/12 ,  G06N20/00 ,  G06F9/48

Abstract: Some embodiments include a method of machine learner workflow processing. For example, a workflow execution engine can receive an interdependency graph of operator instances for a workflow run. The operator instances can be associated with one or more operator types. The workflow execution engine can assign one or more computing environments from a candidate pool to execute the operator instances based on the interdependency graph. The workflow execution engine can generate a schedule plan of one or more execution requests associated with the operator instances. The workflow execution engine can distribute code packages associated the operator instances to the assigned computing environments. The workflow execution engine can maintain a memoization repository to cache one or more outputs of the operator instances upon completion of the execution requests.

公开(公告)号：US10147041B2

公开(公告)日：2018-12-04

申请号：US14799517

申请日：2015-07-14

Applicant: Facebook, Inc.

Inventor： Tianshi Gao ,  Shyamsundar Rajaram ,  Stuart Michael Bowers ,  Mircea Grecu

IPC: G06N5/04 ,  G06N99/00 ,  G06Q30/02

Abstract: Some embodiments include a method of generating a compatibility score for a grouping of objects based on correlations between attributes of the objects. An example grouping is a pair of user and ad. The method may be implemented using a multi-threaded pipeline architecture that utilizes a learning model to compute the compatibility score. The learning model determines correlations between a first object's attributes (e.g., user's liked pages, user demographics, user's apps installed, pixels visited, etc.) and a second object's attributes (e.g., expressed or implied). Example expressed attributes can be targeting keywords; example implied attributes can be object IDs associated with the ad.

公开(公告)号：US20160358101A1

公开(公告)日：2016-12-08

申请号：US14732501

申请日：2015-06-05

Applicant: Facebook, Inc.

Inventor： Stuart Michael Bowers ,  Hussein Mohamed Hassan Mehanna ,  Alisson Gusatti Azzolini ,  Jeffrey Scott Dunn ,  Rodrigo Bouchardet Farnham ,  James Robert Paton ,  Aleksandr Sidorov ,  Pamela Shen Vagata ,  Xiaowen Xie

IPC: G06N99/00

CPC classification number: G06N20/00 ,  G06F8/34 ,  G06F9/453 ,  G06N3/12

Abstract: Some embodiments include an experiment management interface for a machine learning system. The experiment management interface can manage one or more workflow runs related to building or testing machine learning models. The experiment management interface can receive an experiment initialization command to create a new experiment associated with a new workflow. A workflow can be represented by an interdependency graph of one or more data processing operators. The experiment management interface enables definition of the new workflow from scratch or by cloning and modifying an existing workflow. The workflow can define a summary format for its inputs and outputs. In some embodiments, the experiment management interface can automatically generate a comparative visualization at the conclusion of running the new workflow based on an input schema or an output schema of the new workflow.

Abstract translation: 一些实施例包括用于机器学习系统的实验管理界面。 实验管理界面可以管理与建立或测试机器学习模型相关的一个或多个工作流程。 实验管理界面可以接收实验初始化命令来创建与新工作流相关联的新实验。 工作流程可以由一个或多个数据处理运算符的相互依赖关系图表示。 实验管理界面可以从头开始定义新的工作流程，也可以通过克隆和修改现有的工作流程。 工作流程可以为其输入和输出定义汇总格式。 在一些实施例中，实验管理界面可以在基于新工作流的输入模式或输出模式运行新工作流的结束时自动生成比较可视化。

公开(公告)号：US20160300156A1

公开(公告)日：2016-10-13

申请号：US14684041

申请日：2015-04-10

Applicant: Facebook, Inc.

Inventor： Stuart Michael Bowers ,  Parul Agarwal ,  Parv Ajay Oberoi ,  Hussein Mohamed Hassan Mehanna

IPC: G06N99/00

CPC classification number: G06N99/005 ,  G06F8/00 ,  G06F9/46 ,  G06F17/30539

Abstract: Some embodiments include a machine learner platform. The machine learner platform can implement a model tracking service to track one or more machine learning models for one or more application services. A model tracker database can record a version history and/or training configurations of the machine learning models. The machine learner platform can implement a platform interface configured to present interactive controls for building, modifying, evaluating, deploying, or compare the machine learning models. A model trainer engine can task out a model training task to one or more computing devices. A model evaluation engine can compute an evaluative metric for a resulting model from the model training task.

Abstract translation: 一些实施例包括机器学习者平台。 机器学习者平台可以实现模型跟踪服务，以跟踪一个或多个应用服务的机器学习模型。 模型跟踪器数据库可以记录机器学习模型的版本历史和/或训练配置。 机器学习平台可以实现一个平台接口，配置为提供用于构建，修改，评估，部署或比较机器学习模型的交互式控件。 模型训练器引擎可以将模型训练任务排除到一个或多个计算设备。 模型评估引擎可以从模型训练任务计算结果模型的评估度量。

公开(公告)号：US20160283863A1

公开(公告)日：2016-09-29

申请号：US14671657

申请日：2015-03-27

Applicant: Facebook, Inc.

Inventor： Stuart Michael Bowers ,  Hussein Mohamed Hassan Mehanna ,  Andrey Malevich ,  Sai Nishanth Parepally ,  David Paul Capel ,  Alisson Gusatti Azzolini

IPC: G06N99/00

CPC classification number: G06N20/00 ,  G06Q30/00 ,  G06Q50/01

Abstract: An online system identifies an additional feature to evaluate for inclusion in a machine learned model. The additional feature is based on characteristics of one or more dimensions of information maintained by the online system. To generate data for evaluating the additional feature, the online system generates various partitions of stored data, where each partition includes characteristics associated with one or more dimensions on which the additional feature is based. Using values of characteristics in a partition, the online system generates values for the additional feature and includes the values of the additional feature in the partition. Values for the additional feature are generated for various partitions based on the values of characteristics in each partition. The online system combines multiple partitions that include values for the additional feature to generate a training set for evaluating a machine learned model including the additional feature.

Abstract translation: 在线系统识别一个附加功能，以评估包含在机器学习模型中。 附加功能基于由在线系统维护的信息的一个或多个维度的特征。 为了生成用于评估附加特征的数据，在线系统生成存储数据的各种分区，其中每个分区包括与附加特征所基于的一个或多个维相关联的特征。 使用分区中的特征值，在线系统生成附加功能的值，并包括分区中附加功能的值。 基于每个分区中的特征值，为各个分区生成附加功能的值。 在线系统组合多个分区，其中包括附加功能的值，以生成用于评估包含附加功能的机器学习模型的训练集。

公开(公告)号：US20160092786A1

公开(公告)日：2016-03-31

申请号：US14498898

申请日：2014-09-26

Applicant: Facebook, Inc.

Inventor： Hussein Mohamed Hassan Mehanna ,  Stuart Michael Bowers

IPC: G06N99/00

CPC classification number: G06N99/005

Abstract: An online system simplifies modification of features used by machine learned models used by the online system, such as machined learned models with high dimensionality. The online system obtains a superset of features including features used by at least one machine learned model and may include additional features. From the superset of features, the online system generates various groups of features for a machine learned model. The groups of features may be a group including features currently used by the machine learned model, a group including all available features, and one or more intermediate groups. Intermediate groups include various numbers of features from the set selected based on measures of feature impact on the machine learned model associated with various features. A user may select a group of features, test the machine learning model using the selected group, and then launch the tested model based on the results.

Abstract translation: 在线系统简化了在线系统使用的机器学习模型所使用的特征的修改，例如具有高维度的加工学习模型。 在线系统获得了包括由至少一个机器学习模型使用的特征的特征的超集，并且可以包括附加特征。 从功能的超集，在线系统生成机器学习模型的各种功能组。 特征组可以是包括机器学习模型当前使用的特征，包括所有可用特征的组以及一个或多个中间组的组。 中间组根据对与各种特征相关的机器学习模型的特征影响的度量来选择所选集中的各种特征。 用户可以选择一组特征，使用所选择的组测试机器学习模型，然后根据结果启动测试模型。