Abstract: Embodiments relate to a method, an electronic device, and a program product for training an encoder and processing data. The method includes inputting sample point cloud data for an object to an encoder to obtain encoded data for the object, and determining, by transforming the encoded data, a plurality of invariant portions for the object and a plurality of variable portions for the object, an invariant portion in the plurality of invariant portions indicating an invariant feature of the object and a variable portion in the plurality of variable portions indicating a variable feature of the object. The method further includes determining, based on the plurality of invariant portions and the plurality of variable portions, a similarity loss and a spatial loss for the sample point cloud data, and adjusting, based on the similarity loss and the spatial loss, a parameter of the encoder to obtain a trained encoder.

Abstract: Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for molecular docking. The method includes: determining a first feature representation characterizing a first molecule and a second feature representation characterizing a second molecule; determining a candidate region for the first molecule based at least on the first feature representation and the second feature representation, the candidate region comprising multiple candidate positions for docking the first molecule with the second molecule; and for each candidate position of the multiple candidate positions, determining a result of docking the first molecule with the second molecule at the candidate position. With the solution of the present disclosure, it is possible to calculate the docking result for the candidate region for the first molecule rather than the entire region, thereby reducing the amount of computation.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for scheduling computing resources. In a method for scheduling computing resources provided by embodiments of the present disclosure, a computing graph for a neural network is acquired, wherein the computing graph includes at least a plurality of nodes, and each node includes at least an operator for forward propagation of the neural network and a gradient operator of the operator for back propagation of the neural network; and computing resources for the neural network are scheduled based on the computing graph. In this way, a correlation of operators between forward propagation and back propagation may be preserved. In addition, there is no need to schedule computing resources again during back propagation. Resource scheduling for forward propagation and back propagation may be completed simultaneously with only one scheduling operation.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for processing data. The method includes determining encoded data for a target object by performing hybrid encoding on multiple types of data for the target object, the multiple types of data including image data of the target object. The method further includes determining, by transforming the encoded data, an invariant portion for a shape of the target object and a variable portion for an expression of the target object. The method improves data processing efficiency, saves time and computing resources, and reduces the amount of data transmission.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for managing training data. In a method for managing training data provided by embodiments of the present disclosure, in response to a determination that new training data is collected by a sensor, the new training data is stored into a collected data stream of a storage pool; in response to a determination that the new training data and historical data stored in a full data stream of the storage pool are refined into refined training data, the refined training data is stored into a refined data stream of the storage pool; and the new training data is stored into the full data stream. In this way, data streams become clear and storage costs are reduced. This greatly reduces the difficulty of developing complex scenarios such as autonomous driving.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for generating a virtual image. The method includes extracting an audio feature of an audio input of a target object; and acquiring an expression parameter and a pose parameter associated with the target object based on the audio feature. The method further includes generating, based on the audio feature, auxiliary information related to a texture for at least a portion of the target object and a geometric shape of at least a portion of the target object. The method further includes generating a virtual image of the target object based on the expression parameter, the pose parameter, and the auxiliary information.

Abstract: Methods, apparatus, and processor-readable storage media for artificial intelligence-driven avatar-based personalized learning techniques are provided herein.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for generating an avatar. The method includes generating an indication of correlation among image information, audio information, and text information of a video. The method may further include generating, based on the indication of the correlation, a first feature set and a second feature set representing features of a target object in the video, wherein the first feature set represents invariant features of the target object in the video, and the second feature set represents equivariant features of the target object in the video. The method may further include generating the avatar based on the first feature set and the second feature set. With this method, the generated avatar can be made more accurate and vivid with a better effect, while also reducing data annotation cost, improving operation efficiency, and enhancing user experience.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for data augmentation. The method includes: generating a group of candidate images based on a target image by using a thermodynamic genetic algorithm (TDGA) model, the TDGA model being configured to apply one or more operations of a set of predetermined image processing operations during each evolution process; and determining multiple augmented images from the group of candidate images based on free energy of the group of candidate images, the multiple augmented images being determined as belonging to the same classification with the target image. In this way, data augmentation can be efficiently implemented by a thermodynamic genetic algorithm.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for processing data. The method includes determining a reference tensor based on a tensor representing multidimensional data, where the reference tensor is associated with a target tensor. The method further includes decomposing the reference tensor to obtain multiple low-rank tensors, where a rank of each of the low-rank tensors is lower than that of the reference tensor. The method further includes determining the target tensor based on the multiple low-rank tensors so as to determine multidimensional data at a specific moment. By means of embodiments of the present disclosure, the overhead of computing resources may be reduced, and the time for processing data may be reduced.

Abstract: The present disclosure relates to a method, a device, and a program product for training a model. The method includes: receiving at least one unlabeled sample and at least one labeled sample for training a pre-training model, the pre-training model being used to extract features of the samples; creating an undirected graph associated with the pre-training model using the at least one unlabeled sample and a set of training samples associated with the pre-training model; dividing the undirected graph to form a plurality of sub-graphs based on corresponding features of the unlabeled sample and the set of training samples, the plurality of sub-graphs corresponding to a plurality of classifications of the samples, respectively; and training, based on the plurality of sub-graphs and the at least one labeled sample, the pre-training model to generate a training model. A corresponding device and a corresponding computer program product are provided.

Abstract: Embodiments of the present disclosure relate to a computer-implemented method, device, and computer program product. The method includes: determining, based on a set of user behavior data over a first time period, a set of behavioral features for a user behavior over the first time period. The method further includes: determining, based on the set of behavioral features, a set of anomaly scores for the user behavior according to an anomaly detection model. The anomaly detection model is trained based on user behavior data over a second time period. The method further includes: updating a previously determined anomaly score threshold based on comparison of the determined set of anomaly scores with the anomaly score threshold. The anomaly score threshold is used for indicating whether the user behavior is anomalous. By continuously updating the anomaly score threshold, the solution uses the updated anomaly score threshold for anomaly detection of user behavior.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for training a data classification model. The method includes generating a first training rule based on probabilities of classifying a plurality of sample data into corresponding classes by a data classification model. The method also includes generating a second training rule based on relevances of the plurality of sample data to the corresponding classes. In addition, the method also includes training the data classification model using the first training rule and the second training rule. With this method, a data classification model is trained, so that the data classification accuracy of the data classification model and the robustness to noise can be improved.

Abstract: Label inheritance techniques are disclosed for soft label generation in an information processing system that uses machine learning. For example, a method generates at least one label for a given data instance from a training data set useable to train a machine learning-based model. The at least one label is generated by assigning one or more labels associated with one or more ancestors of the data instance such that the data instance inherits the one or more labels associated with the one or more ancestors as the at least one label.

Abstract: Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for training a model. The method may include determining image features, audio features, and text features of a reference object based on reference image information, reference audio information, and reference text information associated with the reference object, respectively. The method may also include constructing a feature tensor from the image features, the audio features, and the text features. In addition, the method may further include decomposing the feature tensor into a first feature vector, a second feature vector, and a third feature vector corresponding to the image features, the audio features, and the text features, respectively, to determine a loss function value of the model. The method may also include updating parameters of the model based on the loss function value.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for content recommendation. A method for content recommendation includes determining a similarity between a first recommendation result and a second recommendation result for a content set. The first recommendation result and the second recommendation result are determined based on different recommendation techniques and respectively indicative of a recommendation degree for each content in the content set. The method further includes adjusting the second recommendation result using the similarity. In addition, the method further includes determining a target recommendation result for the content set based on the first recommendation result and the adjusted second recommendation result. In this manner, the accuracy and stability of the finally obtained recommendation results can be improved.

Abstract: The present disclosure relates to a method, a device, and a program product for managing knowledge graphs. In a method, a historical sequence of knowledge graphs is obtained, wherein the historical sequence includes a plurality of historical knowledge graphs respectively associated with a plurality of historical time points, and a historical knowledge graph in the plurality of historical knowledge graphs includes a plurality of nodes and at least one edge between the plurality of nodes. Based on nodes and edges included in the plurality of historical knowledge graphs, a plurality of subgraphs respectively associated with the plurality of historical knowledge graphs are determined. A sequence feature associated with the historical sequence of the knowledge graphs is determined based on the plurality of subgraphs. A prediction model is trained based on the sequence feature such that the prediction model can describe the correlation among the plurality of historical knowledge graphs.

Abstract: Embodiments of the present disclosure provide a method, a device, and a computer program product for data sharing. The method includes acquiring first parameter information corresponding to a source process and second parameter information corresponding to a target process, and selecting a desired data sharing method from methods for sharing data between the source process and the target process based on the first parameter information and the second parameter information. The method further includes realizing data sharing between the source process and the target process based on the desired data sharing method. Through this solution, the data sharing efficiency between processes can be improved.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for task processing. The method includes: processing, in response to receiving a target task, the target task by a first device using a deployed first model; acquiring a first result determined by the first model, the first result having a first confidence; processing, in response to determining that the first confidence is lower than a first threshold, the target task by a second device using a deployed second model; and acquiring a second result determined by the second model, the first model being constructed by compressing the second model. In this way, the accuracy of task processing can be ensured.

Abstract: Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for data processing. The method disclosed herein includes receiving, at an edge device, new data for training a model, the edge device having stored distilled data used to represent historical data to train the model, the historical data being stored in a remote device, and the amount of the historical data being greater than the amount of the distilled data. The method further includes training the model based on the new data and the distilled data. With the data processing solution of the present disclosure, the model can be trained at the edge device with fewer storage resources based on the distilled data, thereby achieving higher model accuracy.