Structural deep multi-view clustering with integrated abstraction and detail.

Deep multi-view clustering, which can obtain complementary information from different views, has received considerable attention in recent years. Although some efforts have been made and achieve decent performances, most of them overlook the structural information and are susceptible to poor quality views, which may seriously restrict the capacity for clustering. To this end, we propose Structural deep Multi-View Clustering with integrated abstraction and detail (SMVC). Specifically, multi-layer perceptrons are used to extract features from specific views, which are then concatenated to form the global features. Besides, a global target distribution is constructed and guides the soft cluster assignments of specific views. In addition to the exploitation of the top-level abstraction, we also design the mining of the underlying details. We construct instance-level contrastive learning using high-order adjacency matrices, which has an equivalent effect to graph attention network and reduces feature redundancy. By integrating the top-level abstraction and underlying detail into a unified framework, our model can jointly optimize the cluster assignments and feature embeddings. Extensive experiments on four benchmark datasets have demonstrated that the proposed SMVC consistently outperforms the state-of-the-art methods.

Structure-aware deep clustering network based on contrastive learning.

Recently, deep clustering has been extensively employed for various data mining tasks, and it can be divided into auto-encoder (AE)-based and graph neural networks (GNN)-based methods. However, existing AE-based methods fall short in effectively extracting structural information, while GNN suffer from smoothing and heterophily. Although methods that combine AE and GNN achieve impressive performance, there remains an inadequate balance between preserving the raw structure and exploring the underlying structure. Accordingly, we propose a novel network named Structure-Aware Deep Clustering network (SADC). Firstly, we compute the cumulative influence of non-adjacent nodes at multiple depths and, thus, enhance the adjacency matrix. Secondly, an enhanced graph auto-encoder is designed. Thirdly, the latent space of AE is endowed with the ability to perceive the raw structure during the learning process. Besides, we design self-supervised mechanisms to achieve co-optimization of node representation learning and topology learning. A new loss function is designed to preserve the inherent structure while also allowing for exploration of latent data structure. Extensive experiments on six benchmark datasets validate that our method outperforms state-of-the-art methods.

Origin, Evolution, and Research Development of Donkeys.

Lack of archaeological and whole-genome diversity data has restricted current knowledge of the evolutionary history of donkeys. With the advancement of science and technology, the discovery of archaeological evidence, the development of molecular genetics, and the improvement of whole-genome sequencing technology, the in-depth understanding of the origin and domestication of donkeys has been enhanced, however. Given the lack of systematic research, the present study carefully screened and collected multiple academic papers and books, journals, and literature on donkeys over the past 15 years. The origin and domestication of donkeys are reviewed in this paper from the aspects of basic information, cultural origin, bioarcheology, mitochondrial and chromosomal microsatellite sequences, and whole-genome sequence comparison. It also highlights and reviews genome assembly technology, by assembling the genome of an individual organism and comparing it with related sample genomes, which can be used to produce more accurate results through big data statistics, analysis, and computational correlation models. Background: The donkey industry in the world and especially in China is developing rapidly, and donkey farming is transforming gradually from the family farming model to large-scale, intensive, and integrated industrial operations, which could ensure the stability of product quality and quantity. However, theoretical research on donkey breeding and its technical development lags far behind that of other livestock, thereby limiting its industrial development. This review provides holistic information for the donkey industry and researchers, that could promote theoretical research, genomic selection (GS), and reproductive management of the donkey population.