The robustness of intelligent IoT device networking is vital for maintaining communication connectivity within intelligent manufacturing systems, impacting the reliability of the customized Industrial Internet of Things (CuIoT). Current studies enhance network connectivity and resilience against cyber attacks through combinatorial optimization theory by redeploying topologies. However, these approaches often overlook the transformative potential of network motifs in the optimization process. To address this, we introduce CuIoT-MET, an innovative approach that enhances CuIoT robustness by leveraging motif evolutionary transfer knowledge from historical evolution processes. By analyzing changes in connection relationships and emphasizing network motifs' unique contributions, we design a novel robustness metric to optimize the evolutionary trajectory, resulting in more robust CuIoT connection patterns. Extensive experiments show that CuIoT-MET outperforms state-of-the-art methods in improving network robustness.

Efficient task offloading is vital for latency-sensitive Industrial IoT (IIoT) systems. Existing deep learning-based approaches, however, face long training time, poor adaptability, and heavy reliance on labeled data. We propose SRCO, a Semi supervised Reservoir Computing-based Offloading framework that uses a fixed dynamic reservoir and trains only the readout layer, enabling fast model updates with minimal overhead. A semi-supervised strategy further exploits unlabeled data to reduce labeling cost. Experiments show that SRCO improves of floading accuracy by up to 15.6% and reduces training time by up to 59.6% compared with state-of-the-art methods, demonstrating strong efficiency and adaptivity for real-time IIoT applications.

Zero-shot Sketch-based Image Retrieval (ZS-SBIR) is a challenging yet rewarding task, as it demands models to possess both brain- like zero-shot learning and cross-view alignment capabilities. Recent advances suggest that powerful pre-trained vision encoders, such as CLIP, offer a promising alternative for addressing the ZS-SBIR task. However, the problem of simultaneously evoking the zero-shot learning capability and cross-view alignment capability of pre-trained vision encoders has barely been discussed. To this end, we propose the CrOss-view Attention Prompt (COP) framework, which is composed of an Attention Prompt module and a Cross-view Query module. Specifically, we formulate prompt construction as a retrieval problem by introducing a prompt pool and attention mechanism, thereby constructing attention prompts with fine granularity to enhance the zero-shot learning capability. Furthermore, to endow COP with cross-view alignment capabilities, we replace single-view queries with carefully designed cross-view queries, which can be smoothly inserted into the Attention Prompt module. The proposed COP is scenario-agnostic and supports vision encoders with diverse pre-training schemes. Comprehensive experiments show that COP achieves competitive performance in ZS-SBIR, Generalized ZS-SBIR, and Cross-data ZS-SBIR scenarios, regardless of whether it is based on the ImageNet pre-trained vision encoder or the CLIP pre-trained vision encoder.

The robust network topology of the Internet of Things (IoT) system facilitates uninterrupted service provisioning when encountering device failures. Traditional topology optimization strategies use link-level algorithms to design robust network topologies for IoT device deployment, ensuring network resilience against failures. These algorithms struggle to provide a robust topology for large-scale networks due to the high complexity and computational cost of optimizing each link individually. To overcome this limitation, we introduceLEGO-Motif, a motif-based IoT topology generation algorithm inspired by preferential attachment (PA) and evolutionary theory. By sequentially integrating network motifs, similar to assembling LEGO bricks, the algorithm efficiently enhances topology robustness while reducing computational overhead. Specifically, we propose a novel metric based on motif density to measure topology robustness; then, guided by this metric, we design a topology generation algorithm that ensures optimal topology with high robustness against cyberattacks throughout its growth, inspired by an evolutionary neural network framework. The LEGO-Motif algorithm introduces novel recombination, PA-based mutation, and pruning operators to enhance optimization performance and reduce running-time costs. Comprehensive case studies and evaluations show that LEGO-Motif outperforms current topology optimization algorithms, achieving more robust network topologies with reduced running time, which offers a promising optimal solution for deploying the IoT topology.

With the scale of the Internet of Things (IoT) system growing constantly, node failures frequently occur due to device malfunctions or cyberattacks. Existing robust network generation methods utilize heuristic algorithms or neural network approaches to optimize the initial topology. These methods do not explore the core of topology robustness, namely how edges are allocated to each node in the topology. As a result, these methods use massive iterative processes to optimize the initial topology, leading to substantial time overhead when the scale of the topology is large. We examine various robust networks and observe that uniform degree distribution is the core of topology robustness. Consequently, we propose a novel UNIformity driven robusT topologY generation scheme (UNITY) for IoT systems to prevent the node degree from becoming excessively high or low, thereby balancing node degrees. Comprehensive experimental results demonstrate that networks generated with UNITY have an “olive-like” topology consisting of a substantial number of medium-degree nodes and possess strong robustness against both random node failures and targeted attacks. This promising result indicates that the UNITY makes a significant advancement in designing robust IoT systems.

Robust Topology is a key prerequisite to providing consistent connectivity for highly dynamic Internet-of-Things (IoT) applications that are suffering node failures. In this paper, we present a two-step approach to organizing the most robust IoT topology. First, we propose a novel robustness metric denoted as$I$, which is based on network motifs and is specifically designed to sensitively analyze the dynamic changes in topology resulting from node failures. Second, we introduce a Distributed duAl-layer collaborative competition optimization strategy based on Motif density (DAiMo). This strategy significantly expands the search space for optimal solutions and facilitates the identification of the optimal IoT topology. We utilize the motif density concept in the collaborative optimization process to efficiently search for the optimal topology. To support our approach, extensive mathematical proofs are provided to demonstrate the advantages of the metric$I$in effectively perceiving changes in IoT topology and to establish the convergence of the DAiMo algorithm. Finally, we conduct comprehensive performance evaluations of DAiMo and investigate the influence of network motifs on the resilience and reliability of IoT topologies. Experimental results clearly indicate that the proposed method outperforms existing state-of-the-art topology optimization methods in terms of enhancing network robustness.

In resource-constrained and dynamic Industrial Internet of Things (IIoT) environments, ensuring robust and adaptable network topologies remains a significant challenge. Existing reinforcement learning-based approaches tackle topology optimization but face scalability issues due to high computational complexity and latency under strict time constraints. To address these challenges, we propose FRED-ABL (FastRobustnessEnhancement forDynamic IIoT topology optimization withAdaptiveBayesianLearning), a novel paradigm that delivers lightweight topology solutions within a constrained time frame. FRED-ABL introduces an innovative topology structure compression method leveraging auxiliary continuous coding, enabling lossless representation of network structures as model inputs. It further defines a new robustness performance metric that integrates considerations of node failures and connection capabilities, serving as a comprehensive evaluation function. By developing an adaptive Bayesian learning model, FRED-ABL efficiently maps the relationship between topology structures and robustness metrics, enabling rapid optimization while significantly reducing computational overhead. Extensive experiments demonstrate that FRED-ABL consistently outperforms state-of-the-art methods, delivering superior robustness and optimization efficiency even in large-scale IIoT deployments.

Predicting stock trends is a highly rewarding but high-risk endeavor due to the complex interplay of market dynamics, irrational behaviors, and diverse sentiments. Previous studies have used time-series analysis on historical prices or sentiment analysis on textual information. However, these methods often fail to capture the dynamic interactions between text and time-series modalities and overlook the different perspectives embedded in textual data. To address these limitations, we propose the pleno-alignment framework (PAFrame) that enhances multimodal stock information through intermodal and intramodal alignment to capture market dynamics. Our framework first integrates textual and time-series data in a shared representation space to learn modal-invariant information. To tackle divergent sentiments in textual data, we employ a contrastive learning approach to extract abstract semantic meanings from objective and subjective perspectives, thereby improving the robustness of language representations. Finally, we use a hybrid approach that explicitly combines cross-attention mechanisms to create a unified representation and utilizes prompts to implicitly guide language models with numerical financial indicators for final prediction. Our comprehensive experiments on five real-world datasets show that PAFrame outperforms existing methods in predicting stock trends.

With the scale of Internet of Things (IoT) continually expanding, the topology is growing rapidly and the probability of cascading collapse due to node failures or malicious attacks is increasing. The decrease in the Quality of Service (QoS) of IoT could be mitigated by robust topology. Existing optimization strategies usually use heuristic algorithms to enhance topology robustness. However, when the scale of topology is large, these algorithms involve a significant amount of iterative searching for the optimal solution, which is time-consuming and prone to getting stuck into local optimum. To tackle this situation, this study introduces arithmetic encoding and proposes a novel probability-based robust topology generation model that can quickly generate IoT robust topology. We losslessly compress robust topologies using arithmetic encoding and extract their features. Based on the extracting features, we design a unique probability-based topology generation approach that avoids the time overhead of iterative calculations. Experimental results demonstrate that the proposed solution in this paper can construct robust topologies in less time for different network scales.

Fast-advancing mobile communication technologies have increased the scale of the Internet of Things (IoT) dramatically. However, this poses a tough challenge to the robustness of IoT networks when the network scale is large. In this paper, we present DAC-Motif, a distributed co-evolutionary method for optimizing network robustness based on network motifs. Unlike centralized evolutionary optimization approaches, DAC-Motif uses the technique of Divide-And-Conquer (DAC) to divide the large-scale IoT topology into partitions and then merge the self-evolving partitions into a global robust topology. This approach leverages both distributed computing and asynchronous communication mechanisms to mitigate premature convergence and reduce time complexity for large-scale IoT topologies. In our evaluation, DAC-Motif achieves three to four orders of magnitude shorter running time and over 10% robustness improvement compared to other centralized evolutionary algorithms under a scale of around 5,000 IoT devices.

Topology robustness is critical to the connectivity and lifetime of large-scale Internet-of-Things (IoT) applications. To improve robustness while reducing the execution cost, the existing robustness optimization methods utilize neural learning schemes, including neural networks, deep learning, and reinforcement learning. However, insufficient exploration of reinforcement learning agents for topological environments is likely to yield local optima. Moreover, convergence speed is influenced by the sparse reward problem generated while exploring topological environments. To address these problems, this study proposes a self-adaptive robustness optimization method with an evolutionary multi-agent for IoT topology (ROMEM). ROMEM introduces a new multi-agent co-evolution scheme that leverages a non-deterministic strategy to extend the exploration in multi-directions, enabling the reinforcement learning agent to transcend local optima. Furthermore, ROMEM presents a novel distributed training mechanism for multiple agents to accelerate convergence. Experimental results demonstrate that ROMEM can achieve multi-directional collaborative training and outperform other state-of-the-art learning-based robustness optimization methods in terms of convergence efficiency and robustness.

With the rapid scale expansion of the Internet of Things (IoT), the probability of system failure increases. Frequent system failures degrade the quality of service (QoS) of IoT. Existing optimization strategies utilize reinforcement learning (RL) to enhance the robustness of IoT topology. However, due to the increasing scale of the IoT environment, the unbalanced exploration and exploitation of RL agents make it prone to premature convergence at the local optimum. Large-scale action spaces and state spaces lead to a sparse reward problem, which reduces the convergence efficiency of the algorithm. This paper proposes an evolutionary reinforcement learning scheme for IoT robustness to solve the above problems. We design a multi- agent evolution mechanism to provide multiple experiences for RL, which strengthens exploration capability. We present new evolution operators to promote convergence, which combine dis- tillation crossover and Gaussian mutation. Extensive experiments show that our scheme has a strong exploration capability, and the optimization rate of IoT topology robustness reaches 81.15%, which outperforms other robustness optimization algorithms.

Internet of Things (IoT) is growing with various applications linked in, and node failures are becoming more common as a result of malicious strikes and other issues. The cascading collapse induced by local node failures can be mitigated by robust network topology. Existing approaches for fixed topology enhance the robustness of IoT topology by reconstructing device connections. However, using existing techniques necessitates global topology optimization when new nodes are added, which takes time. To tackle this situation, this study introduces an evolutionary algorithm based on neuroevolution that generates robust IoT topology. It provides IoT topology with inherent robustness when adding extra nodes by utilizing unique mutation and crossover operators. What’s more, we establish an adaptive edge density management method to reduce the rise in energy consumption caused by redundant connections when nodes join. Experimental results indicate that the proposed scheme can effectively build robust topology than multiple existing topology optimization methods in less time for diverse network sizes.

Internet of Things (IoT) includes numerous sensing nodes that constitute a large scale-free network. Optimizing the network topology to increase resistance against malicious attacks is a complex problem, especially on 3-dimension (3D) topological deployment. Heuristic algorithms, particularly genetic algorithms, can effectively cope with such problems. However, conventional genetic algorithms are prone to falling into premature convergence owing to the lack of global search ability caused by the loss of population diversity during evolution. Although this can be alleviated by increasing population size, the additional computational overhead will be incurred. Moreover, after crossover and mutation operations, individual changes in the population are mixed, and loss of optimal individuals may occur, which will slow down the population’s evolution. Therefore, we combine the population state with the evolutionary process and propose an Adaptive Robustness Evolution Algorithm (AREA) with self-competition for scale-free IoT topologies. In AREA, the crossover and mutation operations are dynamically adjusted according to population diversity to ensure global search ability. A self-competitive mechanism is used to ensure convergence. We construct a 3D IoT topology that is optimized by AREA. The simulation results demonstrate that AREA is more effective in improving the robustness of scale-free IoT networks than several existing methods.

The span of Internet of Things (IoT) is expanding owing to numerous applications being linked to massive devices. Subsequently, node failures frequently occur because of malicious attacks, battery exhaustion, or other malfunctions. A reliable and robust network topology can alleviate the cascading collapse caused by local node failures. Existing optimization methods for fixed topologies enhance the robustness of the IoT topology by reconstructing the connections among the devices. However, the application of existing algorithms requires global topology optimizations or local adjustments when new nodes are added, which leads to high computational complexity. To address this problem, based on neuroevolution and network motifs, this study proposes an evolutionary algorithm to generate a robust IoT topology called “Born This Way: a self-organizing evolution scheme with Motif” (BTW-Motif). Using novel mutation and crossover operators, BTW-Motif generates an IoT topology with intrinsic robustness when new nodes are added. We design an adaptive edge density control mechanism to avoid an increase in energy consumption resulting from redundant connections. Specifically, BTW-Motif innovatively introduces network motif as a guide structure which has been proven to have a positive effect on the network robustness. Experiments indicate that BTW-Motif can effectively produce a robust topology. With different network sizes and edge densities, BTW-Motif can generate more robust topologies compared with the existing topology optimization algorithms. And the time consumption for the large-scale topology to achieve similar robustness is reduced by 50%.

The Internet of Things (IoT) has been extensively deployed in smart cities. However, with the expanding scale of networking, the failure of some nodes in the network severely affects the communication capacity of IoT applications. Therefore, researchers pay attention to improving communication capacity caused by network failures for applications that require high quality of services (QoS). Furthermore, the robustness of network topology is an important metric to measure the network communication capacity and the ability to resist the cyber-attacks induced by some failed nodes. While some algorithms have been proposed to enhance the robustness of IoT topologies, they are characterized by large computation overhead, and lacking a lightweight topology optimization model. To address this problem, we first propose a novel robustness optimization using evolution learning (ROEL) with a neural network. ROEL dynamically optimizes the IoT topology and intelligently prospects the robust degree in the process of evolutionary optimization. The experimental results demonstrate that ROEL can represent the evolutionary process of IoT topologies, and the prediction accuracy of network robustness is satisfactory with a small error ratio. Our algorithm has a better tolerance capacity in terms of resistance to random attacks and malicious attacks compared with other algorithms.

The extensive applications in the Internet of Things (IoT) have inspired a growing network scale. However, due to the resource-limited IoT devices and the numerous cyber attacks against applications, maintaining the robustness and communication capabilities for the applications is increasingly challenging. In this article, we consider IoT network topologies that provide robust communication for heterogeneous networks and study the networking stability of IoT devices and the intelligent evolution computing in network architectures. We explicate the network robustness problem both for the network architecture and the resistance to cyber attacks. For the network architecture, we optimize the robustness of IoT network topology with a scale-free network model which has good performance in random attacks. In the case with the resistance to cyber attacks, a deep deterministic learning policy (DDLP) algorithm is proposed to improve the stability for large-scale IoT applications. Simulations show that the proposed algorithms greatly advance the robustness of IoT network topology compared to other algorithms, with a less computational cost.