Abstract: According to one aspect of the present disclosure, a computer-implemented method is provided. The method includes obtaining a plurality of user-feature embeddings for a plurality of users. The method includes generating a respective user embedding for each of the plurality of users. The method includes organizing the plurality of users into a plurality of clusters based on user embeddings. The method includes identifying particular clusters based on a respective distance between the plurality of clusters and a particular user embedding of a user. The method may include calculating a respective term-frequency (TF)-inverse document frequency (IDF) (TF-IDF) metric for each content item interacted with by at least one user of that cluster. The method may include assigning a respective rank to the plurality of content items based on the respective TF-IDF metric. The method may include providing one or more of the plurality of candidate content items to a client device.

Abstract: Some implementations relate to a computer-implemented method that includes identifying candidate content items from a set of eligible content items. The computer-implemented method further includes assigning a corresponding rank to each of the candidate content items using an objective function that mitigates a popularity bias among the candidate content items. The computer-implemented method further includes determining an impression-distribution mix of the ranked candidate content items. The computer-implemented method further includes causing one or more of the ranked candidate content items to be displayed based on the impression-distribution mix.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to recommend content items. In some implementations, a method includes identifying candidate content items for recommendation to a user and assigning respective ranks to the candidate content items, wherein the respective ranks are personalized to the user. The method further includes selecting, based on the respective ranks, one or more candidate content items from the candidate content items. The method further includes providing the selected one or more candidate content items to a client device for display in a user interface.

Abstract: A computer-implemented method includes receiving training data that includes groups of items and a respective user associated with each group, where each group includes a first item selected by the associated user and one or more second items rejected by the associated user from a user interface in which the first item and the one or more second items are presented together in ranked order. The method includes, for each group in the group of items: generating feature embeddings, calculating a pointwise loss for each item in the group based on the feature embeddings, calculating a comparator loss for a set that includes the first item and at least one of the one or more second items, and adjusting one or more parameters of the machine learning model based on the pointwise loss and the comparator loss. The method further includes obtaining a trained machine learning model.

Abstract: Methods and systems for low-latency multi-constraint ranking of content items. One of the methods includes receiving a request to rank a plurality of content items for presentation to a user to maximize a primary objective subject to a plurality of constraints; initializing a dual variable vector; updating the dual variable vector, comprising: determining an overall objective score for the dual variable vector; identifying a plurality of candidate dual variable vectors that includes one or more neighboring node dual variable vectors; determining respective overall objective scores for each of the one or more candidate dual variable vectors; identifying the candidate with the best overall objective score; and determining whether to update the dual variable vector based on whether the identified candidate has a better overall objective score than the dual variable vector; and determining a final ranking for the content items based on the dual variable vector.

Abstract: A computer-implemented method to train a machine-learning model to recommend virtual experiences to a user. The method includes receiving training data that includes pairs of users and virtual experiences, wherein each user of a pair is associated with user features, each virtual experience of the pair is associated with item features, and each pair includes a virtual experience that a corresponding user interacted with. The method further includes training a user tower of the machine-learning model by: generating first feature embeddings based on the user features in the training data and training a first deep neural network (DNN) to output user embeddings based on the first feature embeddings. The method further includes training an item tower of the machine-learning model by: generating second feature embeddings based on the item features in the training data and training a second DNN to output item embeddings based on the second feature embeddings.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network used to generate a ranking score for a network input. One of the methods includes generating training data and training the neural network on the training data. The training data includes a plurality of training pairs. The generating comprising: obtaining data indicating that a plurality of training network inputs were displayed in a user interface according to a presentation order, obtaining data indicating that a first training network input of the plurality of training network inputs has a positive label, determining that a second training network input of the plurality of training network inputs (i) has a negative label and (ii) is higher than the first training network input in the presentation order, and generating a training pair that includes the first training network input and the second training network input.

Abstract: A computer-implemented method to train a machine-learning model to recommend virtual experiences to a user. The method includes receiving training data that includes original training examples corresponding to a set of virtual experiences, where individual training examples comprise user features and item features. The method further generating augmented training examples by modifying one or more of a user feature or an item feature from corresponding original training examples. The method further extracting respective representation embeddings from the original training examples and the augmented training examples.

Abstract: Embodiments provide techniques for device power management in wireless networks. For instance, an apparatus may include a power management module, and a transceiver module. The power management module determines a beacon interval and a wakeup interval. The transceiver module to send a transmission to one or more remote devices that includes the beacon interval and the wakeup interval. The beacon interval indicates a time interval between consecutive beacon transmissions of the apparatus, and the wakeup interval indicates a time interval between when the apparatus receives two consecutive beacons from a peer device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for re-ranking a collection of documents according to a first metric and subject to a constraint on a function of one or more second metrics. One of the methods includes: obtaining, for each document in the first collection of documents, a respective first metric value corresponding to the first metric and respective one or more second metric values corresponding to the one or more second metrics; re-ranking the first collection of documents, comprising: determining the constraint on the function of one or more second metrics by computing a first threshold value using a variable threshold function that takes as input second metric values for the documents in the first collection of documents; and determining the re-ranking for the first collection of documents by solving a constrained optimization for the first metric constrained by the first threshold value.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network used to generate a ranking score for a network input. One of the methods includes generating training data and training the neural network on the training data. The training data includes a plurality of training pairs. The generating comprising: obtaining data indicating that a plurality of training network inputs were displayed in a user interface according to a presentation order, obtaining data indicating that a first training network input of the plurality of training network inputs has a positive label, determining that a second training network input of the plurality of training network inputs (i) has a negative label and (ii) is higher than the first training network input in the presentation order, and generating a training pair that includes the first training network input and the second training network input.

Abstract: Embodiments provide techniques for device power management in wireless networks. For instance, an apparatus may include a power management module, and a transceiver module. The power management module determines a beacon interval and a wakeup interval. The transceiver module to send a transmission to one or more remote devices that includes the beacon interval and the wakeup interval. The beacon interval indicates a time interval between consecutive beacon transmissions of the apparatus, and the wakeup interval indicates a time interval between when the apparatus receives two consecutive beacons from a peer device.

Abstract: Methods and systems for low-latency multi-constraint ranking of content items. One of the methods includes receiving a request to rank a plurality of content items for presentation to a user to maximize a primary objective subject to a plurality of constraints; initializing a dual variable vector; updating the dual variable vector, comprising: determining an overall objective score for the dual variable vector; identifying a plurality of candidate dual variable vectors that includes one or more neighboring node dual variable vectors; determining respective overall objective scores for each of the one or more candidate dual variable vectors; identifying the candidate with the best overall objective score; and determining whether to update the dual variable vector based on whether the identified candidate has a better overall objective score than the dual variable vector; and determining a final ranking for the content items based on the dual variable vector.

Abstract: Embodiments provide techniques for device power management in wireless networks. For instance, an apparatus may include a power management module, and a transceiver module. The power management module determines a beacon interval and a wakeup interval. The transceiver module to send a transmission to one or more remote devices that includes the beacon interval and the wakeup interval. The beacon interval indicates a time interval between consecutive beacon transmissions of the apparatus, and the wakeup interval indicates a time interval between when the apparatus receives two consecutive beacons from a peer device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for re-ranking a collection of documents according to a first metric and subject to a constraint on a function of one or more second metrics. One of the methods includes: obtaining, for each document in the first collection of documents, a respective first metric value corresponding to the first metric and respective one or more second metric values corresponding to the one or more second metrics; re-ranking the first collection of documents, comprising: determining the constraint on the function of one or more second metrics by computing a first threshold value using a variable threshold function that takes as input second metric values for the documents in the first collection of documents; and determining the re-ranking for the first collection of documents by solving a constrained optimization for the first metric constrained by the first threshold value.

Abstract: A system is described that relies on a sequence model, having been trained using features extracted from contextual information of a computing device, to determine characteristics of past user interactions that resulted in conversions of items from a computing system. Once trained, the sequence model generates a sequence output that is indicative of characteristics of future user interactions that will result in a future conversion of an item from the computing system. An existing prediction model of the system, having been further trained using the output from the sequence model, identifies a future context during which the future user interactions with the computing system will result in the future conversion. In response to recognizing the future context, the system outputs an indication of the item to facilitate the future conversion.

Abstract: Embodiments provide techniques for device power management in wireless networks. For instance, an apparatus may include a power management module, and a transceiver module. The power management module determines a beacon interval and a wakeup interval. The transceiver module to send a transmission to one or more remote devices that includes the beacon interval and the wakeup interval. The beacon interval indicates a time interval between consecutive beacon transmissions of the apparatus, and the wakeup interval indicates a time interval between when the apparatus receives two consecutive beacons from a peer device.

Abstract: Systems, methods, and computer-readable storage media for distributed and automated prediction of future customer revenue are provided. One method involves accessing data structures, each representing a unique customer, storing a set of customer-specific characteristics, segregating the data structures into groups based on a target amount of data structures for each group, and inputting the customer-specific characteristics into a training model. The method includes generating a set of prediction model parameters for each group by applying the customer-specific characteristics to a training model. The method includes transforming the characteristics of each data structure in a first group into respective future revenue values using a first non-linear prediction model, and the characteristics of data structures in a second group into respective future revenue values using a second prediction model.