Abstract: Systems and methods for recommending content to an online service subscriber are presented. For each subscriber, content items that were the subject of the subscriber's prior interactions are projected, via associated embedding vectors, into a content item embedding space. The content items, via their projections into the content item embedding space, are clustered to form a plurality of interest clusters for the subscriber. A representative embedding vector is determined for each interest cluster, and a plurality of these embedding vectors are stored as the representative embedding vectors for the subscriber. The online service, in response to a request for recommended content for a subscriber, selects a first representative embedding vector associated with the subscriber and identifies a new content item from a corpus of content items according to a similarity measure between the first representative embedding vector and an embedding vector associated with the new content item.

Abstract: Systems and methods for recommending content to an online service subscriber are presented. For each subscriber, content items that were the subject of the subscriber's prior interactions are projected, via associated embedding vectors, into a content item embedding space. The content items, via their projections into the content item embedding space, are clustered to form a plurality of interest clusters for the subscriber. A representative embedding vector is determined for each interest cluster, and a plurality of these embedding vectors are stored as the representative embedding vectors for the subscriber. The online service, in response to a request for recommended content for a subscriber, selects a first representative embedding vector associated with the subscriber and identifies a new content item from a corpus of content items according to a similarity measure between the first representative embedding vector and an embedding vector associated with the new content item.

Abstract: Systems and methods for recommending content to an online service subscriber are presented. For each subscriber, content items that were the subject of the subscriber's prior interactions are projected, via associated embedding vectors, into a content item embedding space. The content items, via their projections into the content item embedding space, are clustered to form a plurality of interest clusters for the subscriber. A representative embedding vector is determined for each interest cluster, and a plurality of these embedding vectors are stored as the representative embedding vectors for the subscriber. The online service, in response to a request for recommended content for a subscriber, selects a first representative embedding vector associated with the subscriber and identifies a new content item from a corpus of content items according to a similarity measure between the first representative embedding vector and an embedding vector associated with the new content item.

Abstract: The disclosed embodiments provide a method and system for performing regularized model adaptation for in-session recommendations. During operation, the system obtains, from a server, a first global version of a statistical model. During a first user session with a user, the system improves a performance of the statistical model by using the first global version to output one or more recommendations to the user and using the first global version and user feedback from the user to create a first personalized version of the statistical model. At an end of the first user session, the system transmits an update containing a difference between the first personalized version and the first global version to the server for use in producing a second global version of the statistical model by the server.

Abstract: A system and method for managing asynchronously receiving updates and merging updates into global versions of a statistical model using version control are disclosed. During operation, the system transmits a first global version of a statistical model to a set of client computer systems. Next, the system obtains, from a first subset of the client computer systems, a first set of updates to the first global version. The system then merges the first set of updates into a second global version of the statistical model. Finally, the system transmits the second global version to the client computer systems asynchronously from receiving a second set of updates to the first and/or second global versions from a second subset of the client computer systems.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a global version of a statistical model and a user-specific version of the statistical model for a user. Next, the system applies the global version to member features of the user and job features of a set of jobs to generate a first ranking of the jobs for the user. The system then applies the user-specific version to the member features and the job features for a highest-ranked subset of jobs in the first ranking to generate a second ranking of the jobs for the user. Finally, the system outputs at least a portion of the second ranking as a set of job recommendations.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a global version of a statistical model and a user-specific version of the statistical model for a user. Next, the system applies the global version to member features of the user and job features of a set of jobs to generate a first ranking of the jobs for the user. The system then applies the user-specific version to the member features and the job features for a highest-ranked subset of jobs in the first ranking to generate a second ranking of the jobs for the user. Finally, the system outputs at least a portion of the second ranking as a set of job recommendations.

Abstract: Learning to rank modeling in the context of an on-line social network is described. A learning to rank model can learn from pairwise preference (e.g., job posting A is more relevant than job posting B for a particular member profile) thus directly optimizing for the rank order of job postings for each member profile. With ranking position taken into consideration during training, top-ranked job postings may be treated by a recommendation system as being of more importance than lower-ranked job postings. In addition, a learning to rank approach may also result in an equal optimization across all member profiles and help minimize bias towards those member profiles that have been paired with a larger number of job postings.