Pruning for content selection

Patent metadata

Field	Value
Publication number	US-12260432-B2
Application number	US-202418616113-A
Country	US
Kind code	B2
Filing date	Mar 25, 2024
Priority date	Sep 22, 2020
Publication date	Mar 25, 2025
Grant date	Mar 25, 2025

Abstract

One or more computing devices, systems, and/or methods are provided. A machine learning model may be trained using a plurality of sets of information. One or more pruning operations may be performed in association with the training to generate a machine learning model with sparse vector representations associated with features of the plurality of sets of information. A request for content associated with a client device may be received. A set of features associated with the request for content may be determined. A plurality of positive signal probabilities associated with a plurality of content items may be determined using the machine learning model based upon one or more sparse vector representations, of the machine learning model, associated with the set of features. A content item may be selected from the plurality of content items for presentation via the client device based upon the plurality of positive signal probabilities.

First claim

What is claimed is:

1. A method, comprising:
receiving a first bid request, wherein:
the first bid request is associated with a first request for content associated with a first client device; and
the first bid request is indicative of a first set of features comprising one or more first features associated with the first request for content;

submitting a first bid value associated with a first content item to a first auction module for participation in a first auction associated with the first request for content;
storing, in an auction information database, a first set of auction information associated with the first auction, wherein:
the first set of auction information is indicative of the first set of features; and
the auction information database comprises a plurality of sets of auction information, comprising the first set of auction information, associated with a plurality of auctions comprising the first auction;

training, in real time, a machine learning model using the plurality of sets of auction information, wherein the training the machine learning model comprises:
performing one or more first training steps to generate a first plurality of weights associated with connections between deep neural network nodes; and
performing one or more second training steps to generate a second plurality of weights;

performing, in an iterative pruning process using the first plurality of weights and the second plurality of weights, one or more pruning operations, in association with the training, to generate a first machine learning model with sparse vector representations associated with features of the plurality of sets of auction information;
receiving a second bid request, wherein:
the second bid request is associated with a second request for content associated with a second client device; and
the second bid request is indicative of a second set of features comprising one or more second features associated with the second request for content;

determining, using the first machine learning model, information based upon one or more first sparse vector representations, of the first machine learning model, associated with the second set of features; and
submitting a second bid value associated with the information to a second auction module for participation in a second auction associated with the second request for content.

2. The method of claim 1 , wherein:
the first set of features comprises a top-level domain associated with an internet resource associated with the first request for content.

3. The method of claim 1 , wherein:
the first set of features comprises a domain name of an internet resource associated with the first request for content.

4. The method of claim 1 , wherein:
the second set of features comprises a device identifier associated with the second client device.

5. The method of claim 1 , wherein:
the performing the one or more pruning operations comprises performing a first iteration of the iterative pruning process by setting a first subset of weights, of the first plurality of weights, to zero to generate a third plurality of weights having a first sparsity; and
the performing the one or more pruning operations comprises performing a second iteration of the iterative pruning process by setting a second subset of weights, of the second plurality of weights, to zero to generate a fourth plurality of weights having a second sparsity.

6. The method of claim 1 , wherein:
the second set of features comprises an internet resource associated with the second request for content.

7. The method of claim 5 , wherein:
the setting the first subset of weights to zero is performed based upon a determination that weights of the first subset of weights are lowest weights of the first plurality of weights; and
the setting the second subset of weights to zero is performed based upon a determination that weights of the second subset of weights are lowest weights of the second plurality of weights.

8. The method of claim 1 , wherein:
the first set of features comprises an internet resource associated with the first request for content.

9. The method of claim 1 , wherein:
the first set of features comprises at least some of a web address of an internet resource associated with the first request for content.

10. The method of claim 1 , comprising:
receiving a click indication indicative of a selection of the first content item via the first client device.

11. The method of claim 10 , wherein the first set of auction information comprises the click indication.

12. A computing device comprising:
a processor; and
memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising:
receiving a first request for content associated with a first client device;
determining, based upon the first request for content, a first set of features associated with the first request for content;
selecting a first content item for presentation via the first client device;
storing, in an information database, a first set of information associated with the first request for content, wherein:
the first set of information is indicative of the first set of features; and
the information database comprises a plurality of sets of information, comprising the first set of information, associated with a plurality of requests for content comprising the first request for content;

training, in real time, a machine learning model using the plurality of sets of information, wherein the training the machine learning model comprises:
performing one or more first training steps to generate a first plurality of weights associated with connections between deep neural network nodes; and
performing one or more second training steps to generate a second plurality of weights;

performing, in an iterative pruning process using the first plurality of weights and the second plurality of weights, one or more pruning operations in association with the training to generate a first machine learning model with sparse vector representations associated with features of the plurality of sets of information;
receiving a second request for content associated with a second client device;
determining, based upon the second request for content, a second set of features associated with the second request for content; and
determining, using the first machine learning model, information based upon one or more first sparse vector representations, of the first machine learning model, associated with the second set of features.

13. The computing device of claim 12 , wherein:
the first set of features comprises at least some of a web address of an internet resource associated with the first request for content.

14. The computing device of claim 12 , wherein:
the first set of features comprises a domain name of an internet resource associated with the first request for content.

15. The computing device of claim 12 , wherein:
the second set of features comprises a location associated with the second client device.

16. The computing device of claim 12 , wherein:
the first set of features comprises an internet resource associated with the first request for content.

17. The computing device of claim 12 , wherein:
the second set of features comprises a device identifier associated with the second client device.

18. The computing device of claim 12 , wherein:
the first set of features comprises a top-level domain associated with an internet resource associated with the

Assignees

• Yahoo Ad Tech Llc

Inventors

• Pan Junwei
• Zhou Tian
• Flores Aaron Eliasib

Classifications

• G06N20/00

  Machine learning · CPC title

• G06N3/082

  modifying the architecture, e.g. adding, deleting or silencing nodes or connections · CPC title

• G06Q30/0275 Primary

  Auctions · CPC title