Replicating human characteristics: A promising animal model of central fatigue.

Central fatigue is a common pathological state characterized by psychological loss of drive, lack of appetite, drowsiness, and decreased psychic alertness. The mechanism underlying central fatigue is still unclear, and there is no widely accepted successful animal model that fully represents human characteristics. We aimed to construct a more clinically relevant and comprehensive animal model of central fatigue. In this study, we utilized the Modified Multiple Platform Method (MMPM) combined with alternate-day fasting (ADF) to create the animal model. The model group rats are placed on a stationary water environment platform for sleep deprivation at a fixed time each day, and they were subjected to ADF treatment. On non-fasting days, the rats were allowed unrestricted access to food. This process was sustained over a period of 21 days. We evaluated the model using behavioral assessments such as open field test, elevated plus maze test, tail suspension test, Morris water maze test, grip strength test, and forced swimming test, as well as serum biochemical laboratory indices. Additionally, we conducted pathological observations of the hippocampus and quadriceps muscle tissues, transmission electron microscope observation of mitochondrial ultrastructure, and assessment of mitochondrial energy metabolism and oxidative stress-related markers. The results revealed that the model rats displayed emotional anomalies resembling symptoms of depression and anxiety, decreased exploratory behavior, decline in learning and memory function, and signs of skeletal muscle fatigue, successfully replicating human features of negative emotions, cognitive decline, and physical fatigue. Pathological damage and mitochondrial ultrastructural alterations were observed in the hippocampus and quadriceps muscle tissues, accompanied by abnormal mitochondrial energy metabolism and oxidative stress in the form of decreased ATP and increased ROS levels. In conclusion, our ADF+MMPM model comprehensively replicated the features of human central fatigue and is a promising platform for preclinical research. Furthermore, the pivotal role of mitochondrial energy metabolism and oxidative stress damage in the occurrence of central fatigue in the hippocampus and skeletal muscle tissues was corroborated.

An End-to-End Deep Graph Clustering via Online Mutual Learning.

In clustering fields, the deep graph models generally utilize the graph neural network to extract the deep embeddings and aggregate them according to the data structure. The optimization procedure can be divided into two individual stages, optimizing the neural network with gradient descent and generating the aggregation with a machine learning-based algorithm. Hence, it means that clustering results cannot guide the optimization of graph neural networks. Besides, since the aggregating stage involves complicated matrix computation such as decomposition, it brings a high computational burden. To address these issues, a unified deep graph clustering (UDGC) model via online mutual learning is proposed in this brief. Specifically, it maps the data into the deep embedding subspace and extracts the deep graph representation to explore the latent topological knowledge of the nodes. In the deep subspace, the model aggregates the embeddings and generates the clustering assignments via the local preserving loss. More importantly, we train a neural layer to fit the clustering results and design an online mutual learning strategy to optimize the whole model, which can not only output the clustering assignments end-to-end but also reduce the computation complexity. Extensive experiments support the superiority of our model.

Manifold Neural Network With Non-Gradient Optimization.

Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may ignore the distribution information of the data during classification. Aiming to tackle the referred problems, we propose a novel manifold neural network based on non-gradient optimization, i.e., the analytical-form solutions. Considering that the activation function is generally invertible, we reconstruct the network via forward ridge regression and low-rank backward approximation, which achieve rapid convergence. Moreover, by unifying the flexible Stiefel manifold and adaptive support vector machine, we devise the novel decision layer which efficiently fits the manifold structure of the data and label information. Consequently, a jointly non-gradient optimization method is designed to generate the network with analytical-form results. Furthermore, an acceleration strategy is utilize to reduce the time complexity for handling high dimensional datasets. Eventually, extensive experiments validate the superior performance of the model.

Geodesic Multi-Class SVM with Stiefel Manifold Embedding.

Manifold of geodesic plays an essential role in characterizing the intrinsic data geometry. However, the existing SVM methods have largely neglected the manifold structure. As such, functional degeneration may occur due to the potential polluted training. Even worse, the entire SVM model might collapse in the presence of excessive training contamination. To address these issues, this paper devises a manifold SVM method based on a novel ξ -measure geodesic, whose primary design objective is to extract and preserve the data manifold structure in the presence of training noises. To further cope with overly contaminated training data, we introduce Kullback-Leibler (KL) regularization with steerable sparsity constraint. In this way, each loss weight is adaptively obtained by obeying the prior distribution and sparse activation during model training for robust fitting. Moreover, the optimal scale for Stiefel manifold can be automatically learned to improve the model flexibility. Accordingly, extensive experiments verify and validate the superiority of the proposed method.