公开(公告)号：US09996804B2

公开(公告)日：2018-06-12

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 ,  G06F9/44 ,  G06F9/46 ,  G06F17/30

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.

公开(公告)号：US10699210B2

公开(公告)日：2020-06-30

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: G06N20/00 ,  G06Q30/00 ,  G06Q50/00

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.

公开(公告)号：US10002329B2

公开(公告)日：2018-06-19

申请号：US14498898

申请日：2014-09-26

Applicant: Facebook, Inc.

Inventor： Hussein Mohamed Hassan Mehanna ,  Stuart Michael Bowers ,  Alexandre Defossez ,  Parv Oberoi ,  Ou Jin

IPC: G06N99/00

CPC classification number: G06N20/00

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.

公开(公告)号：US20170161779A1

公开(公告)日：2017-06-08

申请号：US14960988

申请日：2015-12-07

Applicant: Facebook, Inc.

Inventor： Stuart Michael Bowers ,  Shyamsundar Rajaram ,  Rubinder Singh Sethi

IPC: G06Q30/02

CPC classification number: G06Q30/0247 ,  G06Q30/0255 ,  G06Q30/0275 ,  G06Q30/0277

Abstract: An advertising platform calculates bids for advertisements and optimizes bids for a plurality of advertisement objectives, where each objective corresponds to a unique user action. The advertising platform identifies an impression opportunity for an advertisement request, computes a bid amount for presenting the advertisement, and provides the computed bid amount to an advertisement selection process. The bid amount is computed based on expected values of user actions associated with the plurality of advertisement objectives and an expected value multiplier of one or more advertisement objectives, where the expected value multiplier of the one or more objectives represents a bound on a range of values for the expected values of the user actions associated with the one or more objectives.

公开(公告)号：US20160358102A1

公开(公告)日：2016-12-08

申请号：US14732509

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 ,  G06F17/2705

Abstract: Some embodiments include a workflow authoring tool that accesses a text string representation of a workflow and a text string representation of at least a data processing operator type. The workflow authoring tool enables definition of one or more data processing operator types that can be referenced in defining the machine learning workflow. When scheduling a workflow, the text string representation of the workflow can be parsed and traversed to generate an interdependency graph of one or more data processing operators. The text string representation of the data processing operator type can identify operator attributes associated with the data processing operator type.

Abstract translation: 一些实施例包括访问工作流的文本字符串表示和至少数据处理运算符类型的文本串表示的工作流创作工具。 工作流编辑工具可以定义可以在定义机器学习工作流程时引用的一个或多个数据处理操作员类型。 在调度工作流时，可以对工作流的文本字符串表示进行解析和遍历，以生成一个或多个数据处理运算符的相互依赖关系图。 数据处理运算符类型的文本字符串表示可以识别与数据处理运算符类型相关联的运算符属性。

公开(公告)号：US20150206179A1

公开(公告)日：2015-07-23

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: G06Q30/02 ,  G06Q50/00

CPC classification number: G06Q30/0247 ,  G06Q30/0269 ,  G06Q50/01

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.

Abstract translation: 广告系统具有有限的计算资源，用于评估广告商的广告以确定为社交网络系统的用户服务的“最佳”广告。 基于每次印象的用户和/或广告商的需要，分配计算资源（例如，通过改变被考虑用于呈现给用户的广告的数量）。 可以通过将用户分组并确定使用的每个计算资源的预期收入的收益率曲线来确定用户的需求。 然后，多个用户的展示机会的收入可能会最大化。 广告商的需求可以通过基于预期收入，广告的预期交互次数或以其他方式最大化广告客户的满意度系数来偏移一个广告主的广告的选择而超过另一广告主的广告来确定。

公开(公告)号：US20150088644A1

公开(公告)日：2015-03-26

申请号：US14034338

申请日：2013-09-23

Applicant: Facebook, Inc., a Delaware Corporation

Inventor： Eitan Shay ,  Stuart Michael Bowers ,  Richard Bill Sim ,  Jun Yang

IPC: G06Q30/02

CPC classification number: G06Q30/0254

Abstract: Based on prior interactions associated with a user, an online system predicts an amount of interaction by the user with an object associated with an advertisement. Using the predicted amount of user interaction, the online system determines an expected value of presenting the advertisement to the user. The advertisement is ranked among other advertisements based on the expected values associated with the advertisements, and one or more advertisements are selected for presentation to the user based on the ranking. An advertisement may also specify a threshold amount of interaction with an associated object as targeting criteria, so the predicted amount of interaction with the object associated with the advertisement may determine if a user is eligible to be presented with the advertisement.

Abstract translation: 基于与用户相关联的先前交互，在线系统预测用户与与广告相关联的对象的交互量。 使用预测的用户交互量，在线系统确定向用户呈现广告的期望值。 基于与广告相关联的预期值，广告被排列在其他广告之中，并且基于排名选择一个或多个广告用于呈现给用户。 广告还可以将与相关对象的交互阈值量指定为目标标准，因此与与广告相关联的对象的预测交互量可以确定用户是否有资格被呈现广告。

公开(公告)号：US10740790B2

公开(公告)日：2020-08-11

申请号：US14332167

申请日：2014-07-15

Applicant: Facebook, Inc.

Inventor： Eitan Shay ,  Stuart Michael Bowers ,  Richard Bill Sim ,  Jun Yang

IPC: G06Q30/00 ,  G06Q30/02

Abstract: Based on prior interactions associated with a user, an online system predicts an amount of interaction by the user with an object associated with an advertisement. Using the predicted amount of user interaction, the online system determines an expected value of presenting the advertisement to the user. The advertisement is ranked among other advertisements based on the expected values associated with the advertisements, and one or more advertisements are selected for presentation to the user based on the ranking. An advertisement may also specify a threshold amount of interaction with an associated object as targeting criteria, so the predicted amount of interaction with the object associated with the advertisement may determine if a user is eligible to be presented with the advertisement.

公开(公告)号：US10417577B2

公开(公告)日：2019-09-17

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: G06N3/12 ,  G06N20/00 ,  G06F8/34 ,  G06F9/451

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.

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.).