Abstract: This application describes a data transmission method and a communication apparatus. An example data transmission method includes: performing network coding based on a first data segment, to obtain a first network coded data segment; generating first cyclic redundancy check CRC information and a first data unit based on the first network coded data segment, where the first data unit includes a network coding parameter and the first CRC information that correspond to the first network coded data segment, and the first CRC information is for checking the first network coded data segment; and outputting the first data unit. According to of the example method and communication apparatus of this application, a waste of spectrum resources may be avoided, and spectrum efficiency may be improved.

Abstract: A spectral clustering method and system based on unified anchor and subspace learning is provided. The spectral clustering method based on unified anchor and subspace learning includes: S1: acquiring a clustering task and a target data sample; S2: performing unified anchor learning on multi-view data corresponding to the acquired clustering task and the acquired target data sample, and adaptively constructing an objective function corresponding to an anchor graph according to a learned unified anchor; S3: optimizing the constructed objective function by using an alternating optimization method to obtain an optimized unified anchor graph; and S4: performing spectral clustering on the obtained optimized unified anchor graph to obtain a final clustering result.

Abstract: This application discloses a configuration method for a network coding function and a related apparatus. The network coding function is implemented on a first access network device. Information needed for a terminal device to perform network coding and/or network decoding is configured by the first access network device, to enable network coding and decoding between the first access network device and the terminal device to be possible. After the network coding function is introduced to an access layer, both latency performance and spectral efficiency performance are considered by transmitting an encoded packet. To be specific, the first access network device may flexibly adjust a quantity of sent encoded packets based on quality of an air interface link, to ensure that the terminal device can successfully perform decoding, reducing a data transmission latency while ensuring service transmission reliability.

Abstract: A consensus graph learning-based multi-view clustering method includes: S11, inputting an original data matrix to obtain a spectral embedding matrix; S12, calculating a similarity graph matrix and a Laplacian matrix based on the spectral embedding matrix; S13, applying spectral clustering to the calculated similarity graph matrix to obtain spectral embedding representations; S14, stacking inner products of the normalized spectral embedding representations into a third-order tensor and using low-rank tensor representation learning to obtain a consistent distance matrix; S15, integrating spectral embedding representation learning and low-rank tensor representation learning into a unified learning framework to obtain a objective function; S16, solving the obtained objective function through an alternative iterative optimization strategy; S17, constructing a consistent similarity graph based on the solved result; and S18, applying spectral clustering to the consistent similarity graph to obtain a clustering resul

Abstract: A data sending solution based on a maximum latency constraint T is provided. A transmitting end sends (T+B) data blocks, where first T data blocks are original data blocks, last B data blocks are B encoded data blocks, and a quantity of encoded data packets in the encoded data block is flexible and controllable. A receiving end only needs to perform joint decoding on a specific quantity of encoded data packets and a correct data packet in an incorrect data block, to recover an incorrect data packet in the incorrect data block. The solution in this application can meet a requirement of a maximum latency T, and can reduce a quantity of encoded data packets. The solution may be applied to an XR service or another service that has a low-latency requirement.

Abstract: An unsupervised feature selection method based on latent space learning and manifold constraints includes: S11, inputting an original data matrix to obtain a feature selection model; S12, embedding latent space learning into the feature selection model to obtain a feature selection model with the latent space learning; S13, adding a graph Laplacian regularization term into the feature selection model with the latent space learning to obtain an objective function; S14, solving the objective function by adopting an alternative iterative optimization strategy; and S15, sequencing each feature in the original matrix, and selecting the first k features to obtain an optimal feature subset. Feature selection is performed in a learned potential latent space, and the space is robust to noise. The potential latent space is modeled by non-negative matrix decomposition of a similarity matrix, and the matrix decomposition can unambiguously reflect relationships between data instances.

Abstract: This application provides a communication method and apparatus. In the communication method, a first RLC entity is introduced to transmit a network-coded redundant packet, and a second RLC entity is introduced to transmit a network-coded original packet, so that requirement-based transmission of the network-coded redundant packet can be supported. The communication method includes: A terminal device receives scheduling information from an access network device, obtains a network-coded redundant packet through a first RLC entity, generates a first TB based on the network-coded redundant packet, and sends the first TB to the access network device, where the first TB includes the network-coded redundant packet. In this way, the access network device schedules the network-coded redundant packet by using the scheduling information only when the network-coded redundant packet needs to be scheduled, thereby avoiding a waste and reducing unnecessary redundant transmission.

Abstract: A communication method and apparatus, and a readable storage medium are provided. A network coding NC parameter corresponding to a received index is determined based on a correspondence between the index and an NC parameter, and the NC parameter is applied to NC processing. According to this application, NC processing can adapt to a channel quality state, so that transmission reliability can be ensured and spectrum utilization efficiency can be improved. This application may be applied to an extended reality XR service, a scenario with a low latency and/or a scenario with a large uplink capacity.

Abstract: A multi-view clustering method and system based on matrix decomposition and multi-partition alignment are provided.

Abstract: A late fusion multi-view clustering method and system based on local maximum alignment are provided. The late fusion multi-view clustering method based on local maximum alignment includes the following steps: S1: acquiring a clustering task and a target data sample; S2: initializing a permutation matrix of each view and a combination coefficient of each view, and performing average partition of kernel k-means clustering on an average kernel to obtain a neighbor matrix of each view; S3: calculating basic partition of each view, and establishing a late fusion multi-view clustering objective function based on maximum alignment; S4: acquiring basic partition having local information, and establishing a late fusion multi-view clustering objective function based on local maximum alignment; S5: solving the established late fusion multi-view clustering objective function based on local maximum alignment in a cyclic manner to obtain optimal partition; and S6: performing k-means clustering on the optimal partition.

Abstract: A citation network graph representation learning system and method based on multi-view contrastive learning is provided. The citation network graph representation learning system involved in the present application comprises: a sample construction module, which is configured to construct a corresponding negative sample based on an original graph; a graph enhancement module, which is configured to obtain a positive sample graph and a negative sample graph; a fusion module, which is configured to obtain a consensus representation of the positive sample graph and the negative sample graph by means of a cross view concentration fusion layer; a mutual information estimation module, which is configured to compare learning representations of positive sample pairs and negative sample pairs by means of a discriminator; and a hard sample mining module, which is configured to represent the consistency between the negative sample pairs according to a pre-calculated affinity vector, and select and reserve nodes.

Abstract: A system for unsupervised deep representation learning based on image translation is provided. The system includes an image translation transformation module used for performing a random translation transformation on an image and generating an auxiliary label; an image mask module connected with the image translation transformation module and used for applying a mask to the image after translation transformation; a deep neural network connected with the image mask module and used for predicting an actual auxiliary label of the image after the mask is applied and learning the deep representation of the image; a regression loss function module connected with the deep neural network and used for updating parameters of the deep neural network based on a loss function; and a feature extraction module connected with the deep neural network and used for extracting the representation of the image.

Abstract: A method is provided that a transmitting end generates a data segment, where the data segment includes header information and data parts of a plurality of CBs that are obtained by dividing a TB, there is a position mapping relationship between the data parts of the plurality of CBs and N sub-PDUs included in a MAC PDU, and the header information of each CB indicates a position mapping relationship between the CB and a sub-PDU corresponding to the CB. The transmitting end sends the TB that carries the data segment. Therefore, at a receiving end, if a CRC error occurs on the TB, the receiving end obtains a position of each CB and performs a CRC decision by using a CB as a granularity, to obtain a correct CB. Thereby performance of a wireless communication system is improved.

Abstract: A multi-modal adaptive fusion deep clustering model based on an auto-encoder includes an encoder structure, a multi-modal adaptive fusion layer, a decoder structure and a deep embedding clustering layer. The encoder is configured to enable a dataset to be respectively subjected to three types of nonlinear mappings of the auto-encoder, a convolutional auto-encoder and a convolutional variational auto-encoder to obtain potential features, respectively. The multi-modal adaptive feature fusion layer is configured to fuse the potential features into a common subspace in an adaptive spatial feature fusion mode to obtain a fused feature. The decoder is configured to decode the fused feature by using a structure symmetrical to the encoder to obtain a decoded reconstructed dataset. The deep embedding clustering layer is configured to cluster the fused feature Z and obtain a final accuracy ACC by comparing a clustering result with a true label.

Abstract: The present disclosure discloses an example communication method and apparatus. One example communication method includes receiving, by a first node, decoding information and coded data from a second node, where the coded data is obtained after data of a node group in which the first node is located is encoded, the data of the node group includes data expected to be received by at least two nodes in the node group, and the at least two nodes include the first node. Data expected to be received by the first node is obtained by the first node based on the decoding information and the coded data.

Abstract: This application provides a method for wireless communication and an apparatus. The method includes: receiving, by a communication device, L pieces of first data, and determining reception statuses for the L pieces of first data; receiving, by the communication device, second data, and generating feedback information based on the reception statuses for the L pieces of first data and the second data, where the feedback information indicates one or more reception statuses for M pieces of first data, the M pieces of first data are included in the L pieces of first data; and the second data is data obtained after N pieces of first data are encoded, the N pieces of first data are included in the L pieces of first data; and sending, by the communication device, the feedback information.

Abstract: A coding method and an apparatus are provided. XR data of different dimensions or different QoS requirements are distinguished during coding.

Abstract: Coding method and apparatus provide for coding a to-be-coded data unit to obtain a coded data unit, where a size of the to-be-coded data unit is related to a size of a first data unit. The first data unit is a transport block TB, a protocol data unit PDU, or a service data unit SDU. The first data unit is generated based on the coded data unit.

Abstract: Embodiments of this application provide an encoding method and an apparatus for network encoding. A plurality of to-be-encoded data units are divided into a plurality of groups for separate encoding, and the quantity of to-be-encoded data units included in each group is less than the quantity of all to-be-encoded data units. According to the method, correlation of the encoded data is reduced, and a capability of the encoded data against channel fading and channel change is improved, to increase the receiving reliability of the encoded data.

Abstract: This application describes a data transmission method and a communication apparatus. An example data transmission method includes: performing network coding based on a first data segment, to obtain a first network coded data segment; generating first cyclic redundancy check CRC information and a first data unit based on the first network coded data segment, where the first data unit includes a network coding parameter and the first CRC information that correspond to the first network coded data segment, and the first CRC information is for checking the first network coded data segment; and outputting the first data unit. According to of the example method and communication apparatus of this application, a waste of spectrum resources may be avoided, and spectrum efficiency may be improved.