A method, an apparatus, a computer device, a storage medium, and a program product for processing data are provided, which belong to the technical field of artificial intelligence. The method includes: acquiring model training information transmitted by each of at least two edge node devices, the model training information being transmitted in a form of plaintext, and being obtained by the edge node device by training sub-models through differential privacy; acquiring, based on the model training information transmitted by each of the at least two edge node devices, the sub-models trained by each of the at least two edge node devices; and performing, based on a target model ensemble policy, model ensemble on the sub-models trained by the at least two edge node devices, to obtain a global model. This solution expands the manner of model ensemble while ensuring the data security, thereby improving the model ensemble effect.

A data processing method, apparatus, and device, and a storage medium are provided. The method is performed by a first device in a data processing system, and the method includes: obtaining first sample data of a target service; training a first service processing model based on the first sample data, to obtain a first model parameter of the first service processing model; transmitting, to a second device in the data processing system, the first model parameter, based on which and based on a second model parameter determined by the second device, a first fusion parameter is determined at the second device; obtaining a second fusion parameter, the second fusion parameter comprising model parameters respectively determined by at least three devices in the data processing system; and determining a target model parameter of the first service processing model based on the second fusion parameter.

The present disclosure relates to a communication system based on a neural network model, and a configuration method therefor. The communication system includes at least one master node and multiple child nodes that are in communication connection with the master node, and a child node neural network model is configured in each of the multiple child nodes. The configuration method for the communication system includes: obtaining feature information of the multiple child nodes; and dynamically configuring the child node neural network models on the basis of the obtained feature information.

The present disclosure relates to communication technology, and provides a resource configuration method and apparatus, a device, and a storage medium. The method includes: receiving first resource configuration information from a network device. The first resource configuration information includes n resource configuration combinations each including first-type resource configuration information and second-type resource configuration information, where n is positive integer. The first-type resource configuration information indicates a radio resource configuration, and the second-type resource configuration information indicates an Artificial Intelligence (AI) resource configuration. The combined configuration solution according to the embodiments of the present disclosure can reduce the number of times the network device performs resource scheduling, and reduce the processing overhead of the network device.

Embodiments of the present disclosure relate to a method, a device, and a computer program product for user behavior prediction. In some embodiments, at a client, a first user behavior embedding engine in the client generates behavior prediction information of a target user based on feature information of the target user. The client sends the behavior prediction information of the target user to a server, and receives information about a target item recommended for the target user from the server. Such method enables user privacy-related information to be processed only locally, thereby not only ensuring user privacy and security, but also significantly reducing overall resource overhead.

A system, method, and computer program product for implementing deep learning software model modification is provided. The method includes monitoring operational performance of a software model. An expected confidence level associated with the operational performance is first determined and it is determined that an inference associated with the expected confidence level is below a selected range of inferences associated with assigning new feature data as candidate video data. A candidate sequence comprising video data associated with the candidate video data is received and a similarity between frames of the candidate sequence is determined. A frame comprising a highest similarity with respect to segments of candidate video data is selected and it is detected that the frame is not associated with additional frames stored within a full cache structure. The software model is retrained such that the operational performance is modified.

An information processing system includes a first information processing apparatus including a first inference unit configured to perform first inference processing on inference target medical data using a first partial model including an input layer and at least some of intermediate layers and corresponding to a plurality of second partial models, and a first output unit configured to output a result of the first inference processing and selection information to a second information processing apparatus, and the second information processing apparatus including a second inference unit configured to perform second inference processing by inputting a result of the first inference processing to a second partial model selected from among the plurality of second partial models based on the selection information.

Described are a system, method, and computer program product for user network activity anomaly detection. The method includes receiving network resource data associated with network resource activity of a plurality of users and generating a plurality of layers of a multilayer graph from the network resource data. Each layer of the plurality of layers may include a plurality of nodes, which are associated with users, connected by a plurality of edges, which are representative of node interdependency. The method also includes generating a plurality of adjacency matrices from the plurality of layers and generating a merged single layer graph based on a weighted sum of the plurality of adjacency matrices. The method further includes generating anomaly scores for each node in the merged single layer graph and determining a set of anomalous users based on the anomaly scores.

Methods, systems, apparatuses and computer programs are presented for developing machine-learning models. A method for decentralized machine learning in a target worker node comprises: receiving a plurality of adapted neural network models from a plurality of worker nodes, wherein each of the adapted neural network models is generated by training a worker node neural network using local data of the worker node from among the plurality of worker nodes; selecting, from the plurality of adapted neural network models, a set of adapted neural network models that satisfy performance criteria when local data of the target worker node is input; and averaging the set of adapted neural network models to generate an average model.

A distributed deep learning system includes nodes (1-n, n=1, . . . , 4) and a network. The node (1-n) includes GPUs (11-n-1 and 11-n-2), and an FPGA (12-n). The FPGA (12-n) includes a plurality of GPU reception buffers, a plurality of network transmission buffers that store data transferred from the GPU reception buffers, a plurality of network reception buffers that store aggregated data received from other nodes, and a plurality of GPU transmission buffers that store data transferred from the network reception buffers. The GPUs (11-n-1 and 11-n-2) DMA-transfer data to the FPGA (12-n). The data stored in the GPU transmission buffers is DMA-transferred to the GPUs (11-n-1 and 11-n-2).