Facebook, Inc.

Microsoft Technology Licensing, LLC

Other

Meta Platforms, Inc.

Jason Eric Brewer

Bradley Ray Green

Neeraj Garg

Joshua Richard Williams

Justin Moore

Daniel Jeng-Ping Hui

Mao Xue

Keegan Jones

Anatoliy Panasyuk

Charles Lamanna

Mauktik Gandhi

Jinyi Yao

Travis M White

James Donovan

Jonathan Daniel Sorg

Vikram Kakumani

Komal Kapoor

James Wah Hou Wong

Meiying Li

Apaorn Tanglertsampan

Deepak Chinavle

Theodore E Vanderheyden

Neal Suresh Vora

Gaurav Dosi

Gavarraju Nanduri

Dean Ehnes

Bill Polly

David Tomotsu Sasaki

Systems, methods, and non-transitory computer readable media are configured to apply a spectral clustering technique to at least a portion of a similarity graph to generate clusters of geographic sub-regions constituting geographic regions. A tf-idf technique is performed to determine pages of a social networking system associated with a geographic region as potential local suggestions for a user associated with a geographic sub-region in the geographic region. References to at least a portion of the pages are presented as local suggestions to the user.

Systems and methods to provide local suggestions based on spectral clustering

Systems, methods, and non-transitory computer-readable media can select a set of selected pages from a plurality of pages on a social networking system based on page selection criteria. A set of potential stories from the set of selected pages is aggregated. The set of potential stories are ranked based on ranking criteria. An administrator feed associated with a first page is generated, the administrator feed comprising a plurality of stories from the set of potential stories based on the ranking the set of potential stories.

Systems and methods for providing entity account administrator feeds

Systems, methods, and non-transitory computer-readable media can determine a respective embedding for each entity in a set of entities that are accessible through the social networking system, wherein each embedding is learned based at least in part on one or more sessions of connections formed between users and entities of the social networking system. One or more candidate entities that are related to a first entity can be determined based at least in part on the respective embeddings for the candidate entities and the first entity. At least a first candidate entity from the one or more candidate entities can be provided as a recommendation to a user that formed a connection with the first entity.

Systems and methods for recommending pages

Systems, methods, and non-transitory computer-readable media can determine a plurality of candidate entities for recommendation to a user of a social networking system. A predicted activity objective value model configured to calculate activity stores for candidate entities is established. The activity score is indicative of the probability of future activity on the social networking system by a candidate entity. A first activity score is determined for each of the plurality of candidate entities based on the predicted activity object value model and a first set of feature values. A second activity score is determined for each of the plurality of candidate entities based on the predicted activity object value model and a second set of feature values that is different from the first set of feature values. A first entity is selected of the plurality of candidate entities based on the first and second activity scores.

Systems and methods for predicting page activity to optimize page recommendations

Particular embodiments detect events associated with information about events and activities that a user has engaged in. The events may be of a particular type. An entity associated with an event may request that the user provide further information on the event and, based on the received information, the social-networking system sends the user a request for follow-up information after an appropriate time delay. The time delay may vary based on the user activity and the type or context of the event that triggered the request. After the follow-up information is received, such information is stored in the social-networking system and may be used to determine recommendations, sponsored stories, advertisements, etc. to send to friends of the user. The information may also be used for ranking or filtering recommendations.

Eliciting event-driven feedback in a social network after a time delay

In one embodiment, a method includes receiving a query input, parsing the query input to identify one or more n-grams, determining a search bias of the first user with respect to the query input, the search bias being determined based on an explicit bias and an implicit bias of the first user, wherein the explicit bias is based on an analysis of the entities associated with the online social networking matching n-grams in the query input, and wherein the implicit bias is based on an analysis of user-profile information of a plurality of second users sharing one or more user attributes with the first user, identifying content objects matching the query input based at least in part on the search bias of the first user, and sending instructions for presenting a search-results interface comprising references to the identified content objects.

Determining explicit and implicit user biases for search results on online social networks

Systems, methods, and non-transitory computer-readable media can determine a respective latent representation for each entity in a set of entities that are accessible through the social networking system, wherein a latent representation for an entity is determined based at least in part on a topic model associated with the entity, each latent representation for an entity having a lower dimensionality than a topic model of the entity. One or more candidate entities that are related to a first entity can be determined based at least in part on the respective latent representations for the candidate entities and the first entity. At least a first candidate entity from the one or more candidate entities can be provided as a recommendation to a user that formed a connection with the first entity.

Systems and methods for recommending content items

Systems, methods, and non-transitory computer-readable media can generate layered training data for determining embeddings for entities that are accessible through the social networking system, wherein the layered training data includes layers of data that are organized by a hierarchy, and wherein each layer of data corresponds to entities of a same type. A respective embedding for each entity in a set of entities can be determined, wherein the embeddings are trained iteratively using each layer of data in the layered training data. One or more candidate entities that are related to a first entity can be determined based at least in part on the respective embeddings for the candidate entities and the first entity. At least a first candidate entity from the one or more candidate entities can be provided as a recommendation to a user that formed a connection with the first entity.

Systems, methods, and non-transitory computer readable media configured to determine seed content items based on interests of a user. Candidate content items can be determined for potential presentation to the user based at least in part on the seed content items. Features associated with the candidate content items can be processed to generate probabilities that the user will perform interactions with the candidate content items. Values can be assigned to the candidate content items based on the probabilities that the user will perform interactions with the candidate content items and the importance of the interactions. The values can be provided as bid values to an auction system to determine constraints regarding presentation of the candidate content items. Presentation of the candidate content items can be optimized.

Systems and methods for page recommendations

An online system, such as a social networking system, recommends pages of content to users. The recommendation is presented in a recommendation unit presenting one or more representations of pages to a user. Additionally, the user may interact with the recommendation unit to change representations of pages presented by the recommendation unit. A representation of a page presented by the recommendation unit includes content from one or more content items on the page selected based on interaction with the content items on the page and types of content included in content items on the page (e.g., image data, video data, destination address). Representations of different pages may differ based on the types of content included in content items selected from the different pages.

Recommending pages of content to an online system user by identifying content from recommended pages to the user

In one embodiment, a method includes receiving a query, identifying one or more nodes of a plurality of second nodes corresponding to the query, calculating a score for each of the identified nodes using a probabilistic ranking model that scores each node based at least in part on a number of edges connecting the node to one or more nodes within a first set of user nodes that includes the first node and user nodes corresponding to second users sharing one or more user attributes with the first user, and generating corresponding search results. The score calculated for each of the identified nodes may bias the search results toward nodes connected to disproportionately more nodes in the first set of user nodes than nodes in the plurality of second nodes that correspond to an overall population of users of the online social network.

Search results based on user biases on online social networks

A social networking system recommends pages or other objects to a user with which the user may establish a connection to receive content associated with an object. Candidate objects may be identified by the social networking system as objects connected to additional users who are connected to an object connected to the user. To recommend objects with which the user is likely to have an interest, the social networking system extracts one or more topics from the object connected to the user and from various candidate objects. Based on a topic graph, the social networking system determines measures of relatedness between topics extracted from various candidate objects and an object connected to the user. The measures of relatedness are then used to select one or more of the candidate objects to identify to the user.

Recommending objects to a social networking system user based in part on topics associated with the objects

In one embodiment, a method includes receiving a query, determining a user bias of a first user of an online social network from a first node corresponding to the first user and a plurality of user nodes corresponding to a plurality of second users sharing one or more user attributes with the first user, identifying nodes of a plurality of second nodes based at least in part on the user bias of the first user, where the identified nodes correspond to the structured query, and generating search results corresponding to the identified nodes. The bias may be determined by identifying a candidate user node of the second nodes, comparing a first user attribute of the first node to a second user attribute of the candidate user node, and including the candidate user node in the user nodes when the first user attribute matches the second user attribute.

Identifying user biases for search results on online social networks

Systems, methods, and non-transitory computer readable media configured to determine whether a candidate content item may be presented in response to an indication of approval by a user regarding a seed content item according to a first technique. It is determined whether the seed content item may be presented in response to an indication of approval by the user regarding the candidate content item according to a second technique. Features, including a reciprocity feature based on the determining whether a candidate item may be presented and the determining whether the seed content item may be presented, are processed to generate a probability that the user will interact with the candidate content item.

Systems and methods for page recommendations based on page reciprocity

In order to allow a single user registered on a single local host or other machine to access multiple shared resources on a remote host, an aliasing mechanism is employed so that multiple concurrent connections can be established by the user to a single remote host, with each connection using a different identity. Each connection can therefore be used to access a different shared resource on the remote host. In some illustrative examples, a user's identifier such as his or her machine log-in identification may be associated with two or more resource sharing aliases. As a result, two or more resource sharing sessions can be established by the user with a single remote host, with each of the sessions using a different one of the aliases. The resource sharing sessions are usually established in accordance with a resource sharing protocol such as the Server Block Message (SBM) protocol.

Growing community of inventors

Kirkland, WA, United States of America

Jason Eric Brewer