3 results about "Multiview learning" patented technology

This disclosure provides an entity classification method, apparatus, electronic device, and storage medium. The method includes: acquiring multiple entity relationship networks corresponding to multiple entity nodes; the same entity node corresponding to different entity relationships in different entity relationship networks; performing multi-label prediction on the multiple entity relationship networks based on multiple trained base learners to obtain the multi-label prediction result of each entity node in each entity relationship network; and determining the final multi-label prediction result corresponding to each entity node based on the multi-label prediction result of each entity node in each entity relationship network. This disclosure, from the perspective of multi-view learning, performs multi-label prediction based on multiple entity relationship networks, which can more fully explore the relationships between entities, making the multi-label prediction results for entity nodes more accurate.

The application provides a single-cell multi-modal classification method and system with phased multi-view cooperation, relates to the field of biological information technology, and comprises the following steps: acquiring multi-modal data of a plurality of single cells; performing modal feature screening and normalization processing on the multi-modal data to obtain normalized data of each mode; calculating cell similarity based on the normalized data, and combining a mutual neighbor strategy to construct a cell-cell graph under each mode; performing feature extraction on the normalized data of each mode to obtain cell features under different modes; performing interactive learning according to the cell-cell graph and the cell features, and combining feature refining and multi-view learning to generate a common latent representation matrix; and performing cell type prediction through the common latent representation matrix to obtain the final classification result of each single cell. The application solves the problems that the existing method still has limitations in the depth fusion and calculation efficiency of feature interaction, and cannot balance the complementarity and technical noise of multi-modal data.

The application discloses a high-order anchor graph based semi-non-negative tensor decomposition multi-view clustering method, and belongs to the technical field of multi-view learning and data mining. Firstly, anchor points are selected from multi-view data and an anchor graph tensor reflecting the similarity relationship between samples and anchor points is constructed; then, the tensor is decomposed by using a semi-non-negative tensor decomposition framework to obtain low-dimensional representation satisfying non-negative and orthogonal constraints; further, a high-order anchor graph tensor is constructed by simulating a multi-step random walk process to capture high-order neighbor relationships between samples and anchor points; on this basis, a low-rank tensor constraint based on a logarithmic determinant is applied to the low-dimensional representation to effectively fuse complementary information and spatial structures among multi-views, forming a constrained optimization model; finally, the model is solved by using an alternating optimization algorithm, and clustering is completed according to the obtained low-dimensional representation. The application can efficiently process large-scale data, and the accuracy and robustness of multi-view clustering are significantly improved through high-order relationships and low-rank constraints.