Abstract: Disclosed in the embodiments of the present disclosure are a method and a device for constructing decision trees. A particular embodiment of the method comprises: sending, to at least one client, a request for acquiring statistical information of attribute information of a target category; receiving the statistical information of attribute information of the target category of samples stored by the clients; generating split point information according to the statistical information of attribute information of the target category of samples respectively stored by the clients, and sending the split point information to the at least one client.

Abstract: A technique to compute statistics of data elements include serially inputting the data elements into a compute channel. The compute channel can generate a first running mean and a first running variance associated with data elements of the vector having odd sequence indices, and a second running mean and a second running variance associated with data elements of the vector having even sequence indices. Subsequent to serially inputting data elements into the compute channel, the first running mean and the second running mean are aggregated to generate a mean associated with the data elements of the vector, and the first running variance and the second running variance are aggregated to generate a variance associated with the data elements of the vector.

Abstract: A neural network system for retraining operational neural networks using a synthetic data set generated by a synthetic data generator neural network is provided. The synthetic data generator network comprises an input layer for receiving an input data set; an output layer for outputting the synthetic data set; and a loss function for receiving from each operational network a value of a medical metric. The operational networks each comprise an input layer for receiving the synthetic data set; and an output layer for outputting the value of the medical metric. The synthetic data generator network is trained for generating the synthetic data set based on the loss function comprising a difference of the values of the medical metric. Each operational network is retrained using the synthetic data set.

Abstract: A computer-implemented method for creating a new document space for a content collaboration system is disclosed. The method includes displaying a space-generation graphical user interface on a client device. The space-generation graphical user interface is displayed in response to a request for a new document space creation, and includes a first user input region, a second user input region, and a space-creation control. The method includes, in response to a user selection of the space-creation control, generating the new document space having a set of predefined space settings determined in accordance with a user selection of a particular selectable tab associated with a particular new-space type, generating space content having a space title determined in accordance with a proposed space title in the second user input region; and generating a new space path using a unique space key. The unique space key is generated based on the proposed space title.

Abstract: Methods, systems, apparatuses, devices, and computer program products are described. A group-based communication system may support automatic layout updates for a document space. If a user adds an object into the document space, the system may generate a card representing the object. The card may include a link to a resource external to the document space and a preview image for the object, where the preview image may be rendered based on unfurling the link. The system may update a layout of the document space to include the generated card and may send, for display in a user interface (UI) of a user device, the updated layout. In some examples, a user may select to reposition the card within the UI (e.g., by dragging-and-dropping the card within the document space). The system may further update the layout of the document space based on the repositioning of the card.

Abstract: In some embodiments, an electronic device expands an item of content in accordance with detection of a user's gaze. In some embodiments, an electronic device scrolls text of a content item in accordance with a determination that the user is reading the content item. In some embodiments, an electronic device navigates between user interfaces in accordance with detection of movement of the user's head and detection of the user's gaze. In some embodiments, an electronic device displays augmented content related to a portion of content in accordance with detection of movement of the user's head and detection of the user's gaze in accordance with some embodiments.

Abstract: A method for extracting an explanation from a solution of a global optimization problem derived via an interval analysis is provided. In the context of a global optimization problem characterized by a model, a set of model parameters, and an objective function delimiting relationships between and among the set of model parameters, each model parameter in the set of model parameters corresponding to a unique solution interval of a set of solution intervals, a ranked order of significance for a solution interval in the set of solution intervals as a function of first and second endpoints of the solution interval is derived. Thereafter, an explanation to the solution of the global optimization problem is provided, the explanation embodied in a list or an index that effectively sorts model parameters in the set of model parameters as a function of the ranked order of significance derived for a model parameter's corresponding solution interval.

Abstract: A computer-implemented technique performs machine learning that bypasses the traditional design of loss functions. The technique includes receiving plural instances of gradient objective information. Each of the plural instances includes a particular combination of plural gradient elements. The technique produces plural sets of machine-trained parameter values using the plural respective instances of gradient objective information. The technique performs this operation based on the plural instances of gradient objective information as given, without calculating the plural instances of gradient objective information using loss functions. The technique then measures performance of the plural sets of machine-trained parameter values in an application system. Based on the measured performance, the technique provides output information that identifies a particular set of machine-trained parameter values that satisfies a prescribed test.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed to optimizing engagement with a display during digital assistant-performed operations in response to a received command. The digital assistant generates an overlay having user interface elements that present information determined to be relevant to a user based on the received command and contextual data. The overlay is presented over the underlying operations performed on corresponding applications to mask the visible steps of the operations being performed. In this way, the digital assistant optimizes display resources that are typically rendered useless during the processing of digital assistant-performed operations.

Abstract: A system and method for training relational networks. A method includes applying a self-organizing map (SOM) to training data in order to create a visualization. The SOM is a neural network configured to transform relationships between data items. The visualization has a lower dimensionality than the training data. The method also includes training machine learning models of a generative relational network (GRN) based on the visualization, where the GRN includes sets of nodes having respective machine learning models among the machine learning models of the GRN and the sets of nodes include a set of dominance factor nodes and a set of evolution of internal component nodes. The set of dominance factor nodes defines a dominance factor based on change intensity and change frequency, and the set of evolution of internal component nodes defines evolution with respect to changes determined based on values of the dominance factor over time.

Abstract: A multi-view contrastive relational learning framework is provided. In the multi-view contrastive relational learning framework, contrastive learning is augmented with a multi-view learning signal. The auxiliary views guide an encoder of the underlying time series data's main view, by using an inter-sample similarity structure as a learning signal to learn representations which encode information from multiple views.

Abstract: Decentralized bilevel optimization techniques for personalized learning over a heterogenous network are provided. In one aspect, a decentralized learning system includes: a distributed machine learning network with multiple nodes, and datasets associated with the nodes; and a bilevel learning structure at each of the nodes for optimizing one or more features from each of the datasets using a decentralized bilevel optimization solver, while maintaining distinct features from each of the datasets. A method for decentralized learning is also provided.

Abstract: The present invention relates a method and a system for cross-chain consensus oriented to federated learning, comprising: conducting intra-cluster single-chain federated learning and collecting local update information; sending updates after consensus to a second federation so as to execute cross-cluster gradient exchange; receiving a verification result of cross-cluster gradient update consensus fed back from the second federation; and conducting local model update based on the verification result. After implementation of the update consensus, the present invention provides rewards and punishments based on the contributions of the cluster representatives, thereby encouraging the cluster representatives in the computing nodes to act honestly, so that the participants can actively help the model update.

Abstract: A model generation apparatus according to one or more embodiments may include: a generating unit that generates data using a generation model; a transmitting unit that transmits the generated data to a plurality of trained identification models that each have acquired, by machine learning using local learning data, a capability of identifying whether given data is the local learning data, and causes the identification models to perform an identification on the data; a receiving unit that receives results of identification with respect to the transmitted data executed by the identification models; and a learning processing unit that trains the generation model to generate data that causes identification performance of at least one of the plurality of identification models to be degraded, by performing machine learning using the received results of identification.

Abstract: Computer-implemented methods are provided for generating machine learning model for multimodal data inference tasks. Such a method includes, for each sample in a training dataset of multimodal data samples, encoding the sample to produce a compressed vector representation of the sample in a k-dimensional latent space, and perturbing features of the sample to identify, for each dimension of the latent space, a set of active features perturbation of each of which produces more than a threshold change in the vector representation in that dimension. The method further comprises generating a sample graph having nodes interconnected by edges, wherein the nodes comprise nodes representing respective said features of the sample and edges interconnecting nodes indicate the active features for each dimension. The sample graph is then used to train a graph neural network model to perform the multimodal data inference task. Multimodal data inference systems employing such models are also provided.

Abstract: The present disclosure generally relates to providing media playback controls to a user. In some embodiments, methods and user interfaces for displaying media playback controls are described.

Abstract: A method and system for neural architectural search (NAS) for performing a task. A generative adversarial network comprising a generator and a discriminator receives, from a user device, a query for neural network architecture, the query including a search space. The generator of the generative adversarial network generates a plurality of generated neural network architectures responsive to the received search space. The discriminator of the generative adversarial network selects an optimal neural network architecture from among the plurality of generated neural network architectures. The optimal generated neural network architecture is transmitted to the user device.

Abstract: A method for signal anomaly detection includes receiving at least one signal and determining, using at least one machine learning anomaly detection model, whether a value associated with the at least one signal is within a range of an expected value. The method also includes, in response to a determination that the value associated with the at least one signal is not within the range of the expected value, incrementing a counter, and, in response to a determination that a value of the counter is greater than or equal to a threshold value, identifying, based on the at least one signal, signal anomaly information. The method also includes communicating the signal anomaly information to a remote computing device, receiving, from the remote computing device, diagnostics information responsive to the signal anomaly information, and, in response to receiving the diagnostics information, initiating at least one corrective action procedure.

Abstract: A display unit is connected to an agricultural implement to provide inputs and operational controls, as well as status and set up, of the implement. The display unit can be a touchscreen or other device that can receive inputs to set up, control, store information, and recall information associated with the operation of the agricultural implement. The display unit can provide a number of different types of inputs to allow for the control of the various components of the implement. An alert system can provide tiered alerts, such as based upon the severity of the alerts, to provide for notice to a user as to one or more issues associated with the implement or an operation thereof.

Abstract: Certain aspects of the present disclosure provide techniques for training and using time-domain bootstrapped event prediction models to predict the occurrence of an event within a software application. An example method generally includes receiving a data set of user activity within a software application. A request to predict a likelihood of an event occurring with respect to the software application based on the user activity is received. A likelihood of the event occurring is predicted using an event prediction model. The event prediction model is generally configured to predict the likelihood of the event occurring based on a likelihood over each of a plurality of non-overlapping time windows. A likelihood of the event occurring within a first time window is conditioned on a likelihood of the event occurring within a second time window. One or more actions are taken within the software application based on the predicted likelihood.