Abstract: A method is provided, including: detecting interactions by a plurality of users with a plurality of content items, each content item having an associated content item vector; for a given user, identifying interactions occurring during a current time period, including identifying positive interactions with a first set of the content items, and negative interactions with a second set of the content items; processing a first set of the content item vectors that are associated with the first set of the content items to determine a positive interaction vector; processing a second set of the content item vectors that are associated to the second set of the content items to determine a negative interaction vector; for the given user, generating a current user profile vector for the current time period, using the positive interaction vector, the negative interaction vector, and a prior user profile vector for a prior time period.

Abstract: Methods and systems for ranking a plurality of articles for rendering on a website for a user account include receiving a request for accessing the website. Features are identified for the plurality of articles selected for rendering on the website. Each feature is associated with a value parameter having a value in a multi-dimensional vector space. A pair of solutions is identified for an article of the plurality of articles, wherein the pair of solutions identifies a portion of the multi-dimensional vector space that satisfies multiple objectives. A vector point defining the optimal solution is selected for the article from within the portion of the multi-dimensional vector space. The selected vector point is used in computing an article score for the article. The article score for the plurality of articles is used to identify and present a subset of the articles on the website for the user.

Abstract: A method is provided, including: processing interactions by a plurality of users with a plurality of content items, the content items being provided over a network in response to user requests received over the network, wherein each content item is associated with one or more entities; for each user, determining a user entity set that includes entities associated with content items with which the user interacted; embedding the users and the entities in a vector space, wherein the embedding is configured to place a given user, and the entities of the given user's user entity set, in proximity to each other in the vector space; for each user, performing a proximity search in the vector space to identify a set of nearest entities to the user in the vector space; for each user, generating a user profile using the identified set of nearest entities to the user.

Abstract: A method implemented by at least one server computer is provided, including the following operations: receiving a plurality of training documents, each training document being defined by a sequence of words, each training document having one or more labels associated therewith; embedding the training documents, the words, and the labels in a vector space, wherein the embedding is configured to locate a given training document and its associated labels in proximity to each other in the vector space; embedding a new document in the vector space; performing a proximity search in the vector space to identify a set of nearest labels to the new document in the vector space; associating the nearest labels to the new document.

Abstract: Software for a website hosting a content-aggregation service generates a first representation of interests for a user. The first representation includes a plurality of entities including pivot entities and extended entities, where the extended entities result from a nearest-neighbor search of word embeddings. Each of the extended entities is associated with a nearness score that is weighted using a distance of the extended entity from one of the pivot entities. For each of a plurality of articles ingested by the content-aggregation service, the software generates a second representation that associates an aboutness score with each of the plurality of entities. The software uses the first representation, a similarity measure, and the second representations to create rankings of the plurality of articles. The software receives a request for access to the content-aggregation service from the user and serves the user a content stream based at least in part on the rankings.

Abstract: Software for a content-aggregation website generates a first representation of interests for a geographical location. The representation includes a plurality of entities that are derived from a corpus of documents. Each of the plurality of entities is associated with an expected value that is based on engagement signals from users in the geographical location and that is weighted using a sparse-polarity approach to be discriminative with respect to other entities. Each of the ingested articles is represented by the second representation that associates an aboutness score with each of the plurality of entities. The software uses the first representation, a similarity measure, and a second representation to create rankings of a plurality of ingested articles received. Then the software receives a request for access to the content-aggregation service from a new user from the geographical location and serves the new or infrequent user a content stream based on the rankings.

Abstract: A method implemented on a computing device having at least one processor, storage, and a communication platform connected to a network for multi-label prediction comprises generating a label space; receiving a data point from a user; generating a first feature vector from the data point; projecting the first feature vector to the label space; determining a first set of labels associated with the first feature vector from the label space; converting the first set of labels to a second set of labels; and providing the second set of labels to the user.

Abstract: An input image is denoised by first constructing a pixel-wise noise variance map from the input image. The noise has spatially varying variances. The input image is partitioned into patches using the noise variance map. An intermediate image is determined from the patches. Collaborative filtering is applied to each patch in the intermediate image using the noise variance map to produce filtered patches. Then, the filtered patches are projected to an output image.

Abstract: An input image is denoised by first constructing a pixel-wise noise variance map from the input image. The noise has spatially varying variances. The input image is partitioned into patches using the noise variance map. An intermediate image is determined from the patches. Collaborative filtering is applied to each patch in the intermediate image using the noise variance map to produce filtered patches. Then, the filtered patches are projected to an output image.