Abstract: Certain aspects of the present disclosure provide techniques for relaying physical sidelink control channel in sidelink communications. A method that may be performed by a first user equipment (UE) includes receiving a sidelink control information (SCI) transmission from a second UE, the SCI pointing to one or more resources for a retransmission of the SCI by the second UE. The method may include transmitting the SCI to a third UE using the one or more resources for the retransmission of the SCI by the second UE.

Abstract: An example system includes a processor to receive data for a multi-objective task. The processor is to also perform the multi-objective task on the received data via a trained primal network. The primal network and a dual network are trained for a multi-objective task using a Lagrangian loss function representing a number of objectives. The primal network is trained to minimize the Lagrangian loss function and the dual network is trained to maximize the Lagrangian loss function.

Abstract: An example system includes a processor to receive a prefix of conversation and a text input. The processor is to also generate a completed response based on the prefix of conversation and the text input via a trained primal network. The primal network is trained to minimize a Lagrangian loss function representing a number of objectives and a dual network is trained to maximize the Lagrangian loss function.

Abstract: A method, computer system, and a computer program product for enhanced rating predictions is provided. The present invention may include receiving a user input. The present invention may then include translating the received user input into an embedding matrix and inputting the embedding matrix into a deep neural network. The present invention may further include generating, by the deep neural network, an output vector, a user bias term and an item bias term based on the embedding matrix. The present invention may then include calculating a predicted rating based on the generated output vector, the generated user bias term and the generated item bias term. The present invention may then include determining an accuracy of the predicted rating.

Abstract: An example system includes a processor to receive data for a multi-objective task. The processor is to also perform the multi-objective task on the received data via a trained primal network. The primal network and a dual network are trained for a multi-objective task using a Lagrangian loss function representing a number of objectives. The primal network is trained to minimize the Lagrangian loss function and the dual network is trained to maximize the Lagrangian loss function.

Abstract: An example system includes a processor to receive a prefix of conversation and a text input. The processor is to also generate a completed response based on the prefix of conversation and the text input via a trained primal network. The primal network is trained to minimize a Lagrangian loss function representing a number of objectives and a dual network is trained to maximize the Lagrangian loss function.

Abstract: A method, computer system, and a computer program product for enhanced rating predictions is provided. The present invention may include receiving a user input. The present invention may then include translating the received user input into an embedding matrix and inputting the embedding matrix into a deep neural network. The present invention may further include generating, by the deep neural network, an output vector, a user bias term and an item bias term based on the embedding matrix. The present invention may then include calculating a predicted rating based on the generated output vector, the generated user bias term and the generated item bias term. The present invention may then include determining an accuracy of the predicted rating.