-
1.发明授权公开(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
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.
-
Patent Agency Ranking
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
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：US11068802B2
公开(公告)日：2021-07-20
申请号：US15638210
申请日：2017-06-29
Applicant: Facebook, Inc.
Inventor： Andrey Malevich , Ou Jin
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 parameters). The platform generates a model for a metric of interest based on a known training set. The model includes parameters indicating importances of different features of the model, taken both singly and in pairs. The model may be applied to predict a value for the metric for given sets of objects, such as for a pair consisting of a user object and a content item object.
-
4.发明申请公开(公告)号：US20200272943A1
公开(公告)日：2020-08-27
申请号：US16869382
申请日：2020-05-07
Applicant: Facebook, Inc.
Inventor： Stuart Michael BOWERS , Hussein Mohamed Hassan Mehanna , Andrey Malevich , Sai Nishanth Parepally , David Paul Capel , Alisson Gusatti Azzolini
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：US20190005406A1
公开(公告)日：2019-01-03
申请号：US15638210
申请日：2017-06-29
Applicant: Facebook, Inc.
Inventor： Andrey Malevich , Ou Jin
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 parameters). The platform generates a model for a metric of interest based on a known training set. The model includes parameters indicating importances of different features of the model, taken both singly and in pairs. The model may be applied to predict a value for the metric for given sets of objects, such as for a pair consisting of a user object and a content item object.
-
6.发明申请Evaluating Modifications to Features Used by Machine Learned Models Applied by an Online System 审中-公开评估由在线系统应用的机器学习模型使用的特征的修改公开(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
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。
-
-
-
-
-
Search Results
6
records
(took 0.016 seconds)
