A Multitask Network Robustness Analysis System Based on the Graph Isomorphism Network.

Despite various measures across different engineering and social systems, network robustness remains crucial for resisting random faults and malicious attacks. In this study, robustness refers to the ability of a network to maintain its functionality after a part of the network has failed. Existing methods assess network robustness using attack simulations, spectral measures, or deep neural networks (DNNs), which return a single metric as a result. Evaluating network robustness is technically challenging, while evaluating a single metric is practically insufficient. This article proposes a multitask analysis system based on the graph isomorphism network (GIN) model, abbreviated as GIN-MAS. First, a destruction-based robustness metric is formulated using the destruction threshold of the examined network. A multitask learning approach is taken to learn the network robustness metrics, including connectivity robustness, controllability robustness, destruction threshold, and the maximum number of connected components. Then, a five-layer GIN is constructed for evaluating the aforementioned four robustness metrics simultaneously. Finally, extensive experimental studies reveal that 1) GIN-MAS outperforms nine other methods, including three state-of-the-art convolutional neural network (CNN)-based robustness evaluators, with lower prediction errors for both known and unknown datasets from various directed and undirected, synthetic, and real-world networks; 2) the multitask learning scheme is not only capable of handling multiple tasks simultaneously but more importantly it enables the parameter and knowledge sharing across tasks, thus preventing overfitting and enhancing the performances; and 3) GIN-MAS performs multitasks significantly faster than other single-task evaluators. The excellent performance of GIN-MAS suggests that more powerful DNNs have great potentials for analyzing more complicated and comprehensive robustness evaluation tasks.

Reweighted Alternating Direction Method of Multipliers for DNN weight pruning.

As Deep Neural Networks (DNNs) continue to grow in complexity and size, leading to a substantial computational burden, weight pruning techniques have emerged as an effective solution. This paper presents a novel method for dynamic regularization-based pruning, which incorporates the Alternating Direction Method of Multipliers (ADMM). Unlike conventional methods that employ simple and abrupt threshold processing, the proposed method introduces a reweighting mechanism to assign importance to the weights in DNNs. Compared to other ADMM-based methods, the new method not only achieves higher accuracy but also saves considerable time thanks to the reduced number of necessary hyperparameters. The method is evaluated on multiple architectures, including LeNet-5, ResNet-32, ResNet-56, and ResNet-50, using the MNIST, CIFAR-10, and ImageNet datasets, respectively. Experimental results demonstrate its superior performance in terms of compression ratios and accuracy compared to state-of-the-art pruning methods. In particular, on the LeNet-5 model for the MNIST dataset, it achieves compression ratios of 355.9× with a slight improvement in accuracy; on the ResNet-50 model trained with the ImageNet dataset, it achieves compression ratios of 4.24× without sacrificing accuracy.

A chaotic spiking backpropagation approach to brain learning.

A highlight of the chaotic spiking backpropagation (CSBP) method, which is a powerful tool for directly training spiking neural networks and helps to understand the learning mechanisms of human brain.

Delay-driven phase transitions in an epidemic model on time-varying networks.

A complex networked system typically has a time-varying nature in interactions among its components, which is intrinsically complicated and therefore technically challenging for analysis and control. This paper investigates an epidemic process on a time-varying network with a time delay. First, an averaging theorem is established to approximate the delayed time-varying system using autonomous differential equations for the analysis of system evolution. On this basis, the critical time delay is determined, across which the endemic equilibrium becomes unstable and a phase transition to oscillation in time via Hopf bifurcation will appear. Then, numerical examples are examined, including a periodically time-varying network, a blinking network, and a quasi-periodically time-varying network, which are simulated to verify the theoretical results. Further, it is demonstrated that the existence of time delay can extend the network frequency range to generate Turing patterns, showing a facilitating effect on phase transitions.

An "Observable" horseshoe map.

In this article, a family of diffeomorphisms with growing horseshoes contained in global attracting regions is presented, where the dimension of the unstable direction can be any fixed integer and a growing horseshoe means that the number of the folds of the horseshoe is increasing as a parameter is varied. Moreover, it is demonstrated that the horseshoe-like attractors are observable for certain parameters.

Integrated Multiomics Reveals Silencing of has_circ_0006646 Promotes TRIM21-Mediated NCL Ubiquitination to Inhibit Hepatocellular Carcinoma Metastasis.

Recent studies suggest that circular RNA (circRNA)-mediated post-translational modification of RNA-binding proteins (RBP) plays a pivotal role in metastasis of hepatocellular carcinoma (HCC). However, the specific mechanism and potential clinical therapeutic significance remain vague. This study attempts to profile the regulatory networks of circRNA and RBP using a multi-omics approach. Has_circ_0006646 (circ0006646) is an unreported circRNA in HCC and is associated with a poor prognosis. Silencing of circ0006646 significantly hinders metastasis in vivo. Mechanistically, circ0006646 prevents the interaction between nucleolin (NCL) and the E3 ligase tripartite motif-containing 21 to reduce the proteasome-mediated degradation of NCL via K48-linked polyubiquitylation. Furthermore, the change of NCL expression is proven to affect the phosphorylation levels of multiple proteins and inhibit p53 translation. Moreover, patient-derived tumor xenograft and lentivirus injection, which is conducted to simulate clinical treatment confirmed the potential therapeutic value. Overall, this study describes the integrated multi-omics landscape of circRNA-mediated NCL ubiquitination degradation in HCC metastasis and provides a novel therapeutic target.

Heterogeneously Networked Evolutionary Games With Intergroup Conflicts.

Network games primarily explore the intricacies of individual interactions and adaptive strategies within a network. Building upon this framework, the present study delves into the modeling, analysis, and control of heterogeneously networked evolutionary games with intergroup conflicts heterogeneously networked evolutionary games with intergroup conflict (HNEG-IC), where attacking players possess area-monitoring capabilities with limited attacking power. To begin with, a mathematical model is introduced to capture intragroup strategy dynamics and intergroup conflicts of HNEGs-IC via the algebraic state space representationalgebraic state space representation (ASSR). A necessary and sufficient condition for achieving global cooperation of HNEGs-IC is established. Then, a criterion for verifying the κ -cooperation below a certain mortality is presented. Considering the HNEGs-IC with strategy feedback control, it is proven that the feedback control, subject to global cooperation, is robust to conflicts when the intersection of the strategy threshold set and the reachable set of the preset initial strategy profiles is empty. Finally, for verification and demonstration, the obtained results are applied to a simplified virtual game model of the NATO and the Warsaw Pact.

Cooperative Time-Varying Formation Fuzzy Tracking Control of Multiple Heterogeneous Uncertain Marine Surface Vehicles With Actuator Failures.

This article addresses the cooperative time-varying formation fuzzy tracking control problem for a cluster of heterogeneous multiple marine surface vehicles subject to unknown nonlinearity and actuator failures. The proposed cooperative control scheme consists of two parts: 1) a distributed time-varying formation observer and 2) a decentralized adaptive fuzzy tracking controller. The distributed observer is designed to obtain a predefined time-varying formation pattern under a directed communication topology. Subsequently, based on the states of the distributed observer, a decentralized fuzzy tracking control law is developed using fuzzy-logic systems and the adaptive approach. Lyapunov functions are constructed to guarantee that the controlled marine vehicles attain the desired time-varying formation with asymptotical stability of tracking errors. Finally, simulation results are presented to validate the efficacy of the proposed control methodology.

Role of the immune system in liver transplantation and its implications for therapeutic interventions.

Liver transplantation (LT) stands as the gold standard for treating end-stage liver disease and hepatocellular carcinoma, yet postoperative complications continue to impact survival rates. The liver's unique immune system, governed by a microenvironment of diverse immune cells, is disrupted during processes like ischemia-reperfusion injury posttransplantation, leading to immune imbalance, inflammation, and subsequent complications. In the posttransplantation period, immune cells within the liver collaboratively foster a tolerant environment, crucial for immune tolerance and liver regeneration. While clinical trials exploring cell therapy for LT complications exist, a comprehensive summary is lacking. This review provides an insight into the intricacies of the liver's immune microenvironment, with a specific focus on macrophages and T cells as primary immune players. Delving into the immunological dynamics at different stages of LT, we explore the disruptions after LT and subsequent immune responses. Focusing on immune cell targeting for treating liver transplant complications, we provide a comprehensive summary of ongoing clinical trials in this domain, especially cell therapies. Furthermore, we offer innovative treatment strategies that leverage the opportunities and prospects identified in the therapeutic landscape. This review seeks to advance our understanding of LT immunology and steer the development of precise therapies for postoperative complications.