Federated learning (FL) is promising for privacy-sensitive fault diagnosis in the Industrial Internet of Things (IIoT). However, real-world deployments must address the coexistence of class-incremental fault evolution and dynamic edge participation, which leads to fragmented class exposure, catastrophic forgetting, and aggregation bias. To address this issue, we propose FedDiDy, a unified framework for federated class-incremental fault diagnosis under dynamic participation. FedDiDy combines a multi-head classifier for task decoupling, a raw-data-free conditional generator for historical knowledge replay, and a perception-aware aggregation mechanism for bias mitigation. Experiments on four datasets under Bernoulli, Cyclic, and Markov participation patterns show that FedDiDy consistently outperforms the compared baselines, with up to 15.1% absolute improvement in average accuracy and 14.44% reduction in forgetting rate.

Class-incremental continual learning on hypergraphs is challenging under limited replay memory. Buffered samples do not contribute equally to preserving historical higher-order structures. Existing replay methods mainly use random selection or loss-based selection. However, they often ignore structural cohesiveness. As a result, structurally important samples may be missed. We propose KTR ( K nowledge-preserving T russ-based R eplay), a structure-aware replay framework for continual learning on hypergraphs. KTR prioritizes buffered samples by combining hypertuss-based structural importance with current loss-based utility. It further performs constrained replay through structural filtering and probabilistic sampling. The framework supports both node classification and hyperedge classification. Experiments on four continual hypergraph benchmarks show that KTR improves replay performance under limited-memory settings, with the clearest gains on temporal hyperedge-classification benchmarks. Under the HGNN+ backbone with memory budget b = 0.1 , KTR improves ACC by up to 20.32 percentage points and reduces forgetting by up to 24.07 percentage points relative to PBR on MAG-Top20K. On node-classification benchmarks, KTR remains competitive with strong replay baselines, but it does not uniformly dominate all methods on every dataset. These results support the use of structure-aware replay in continual hypergraph learning, especially when higher-order structural cohesion provides informative replay signals.

The decentralized nature of federated learning (FL) makes it difficult to verify the trustworthiness of participating clients, creating an opportunity for backdoor attacks. This paper addresses a general backdoor-resilient decentralized FL problem without any prior knowledge of the type of backdoor attacks or information about malicious clients. After an in-depth investigation of how backdoor attacks are conducted in FL, we introduce a multi-armed bandit-based knowledge distillation approach to help benign clients learn useful knowledge from other clients while rejecting potential backdoors hidden in shared updates. Unlike most previous works that rely on identifying and removing malicious updates—an approach limited to scenarios with fewer than 50% attackers—our knowledge distillation technique enables benign clients to reject backdoored knowledge while preserving useful information, maintaining effective defense even when malicious clients exceed 50% of the population. Additionally, to handle the various updates from clients with Non-IID dataset, a multi-armed bandit scheme is designed for each benign client to select the most appropriate teachers for knowledge distillation, resulting in high accuracy and fast convergence. Extensive experiments demonstrate that our multi-armed bandit-based knowledge distillation approach achieves high accuracy and general backdoor resilience. Comparisons with previous works show that our approach can reduce the attack success rate by 14.71%∼96.78% on average.

This paper studies an efficient federated learning (FL) problem involving multiple edge-based clients with heterogeneous constrained resources. Compared with numerous training parameters, the computing and communication resources of clients in edge scenarios are usually insufficient for fast local training and real-time knowledge sharing. Besides, training on clients with heterogeneous resources may result in the straggler problem, which delays the convergence of FL. To address these issues, we proposeFed-RAA: aResource-AdaptiveAsynchronousFederated learning algorithm. Different from vanilla FL methods, where all parameters are trained by each participating client regardless of resource diversity, Fed-RAA adaptively allocates submodels of the global model to clients based on their computing and communication capabilities. Each client then individually trains its assigned submodel and asynchronously uploads the updated result. Theoretical analysis confirms the convergence of our approach. Additionally, an online greedy-based algorithm is designed for asynchronous submodel assignment in Fed-RAA, improving the convergence of Fed-RAA by optimal minimization on the training delay bound of submodels. Compared to state-of-the-art methods, our Fed-RAA algorithm reduces the time required to achieve the target accuracy by an average of$ 30.89\%$, demonstrating its superior efficiency on heterogeneous constrained computing and communication resources. To the best of our knowledge, this paper is the first resource-adaptive asynchronous method for submodel-based FL with guaranteed theoretical convergence.

Traditional nursing activity recognition relies on manual observation and documentation, which are timeconsuming and error-prone. This paper presents CareAttenNet, a deep learning framework integrating adaptive feature selection, correlation-aware processing, and temporal attention mechanisms for automated nursing activity recognition from wearable sensor data. We evaluated the framework using the SONAR dataset comprising 70-dimensional sensor features from 14 healthcare professionals performing 23 nursing activities, totaling$7,631,843$temporal measurements. CareAttenNet achieved 77.36 % validation accuracy and 60.00 % test accuracy, outperforming baseline architectures including CNN-LSTM (57.92 %), Correlation-Aware CNN$(54.62 \%)$, and Feature-Selective Network$(52.86 \%)$. Ablation studies revealed temporal attention as the most effective component (78.33 % test accuracy), while feature selection combined with temporal attention achieved 77.40 % accuracy. However, combining all components resulted in performance degradation, indicating complex negative interactions between architectural modules. These findings provide insights into multi-modal sensor fusion challenges and establish a foundation for intelligent healthcare monitoring systems.

Federated Learning(FL) is currently a widely used collaborative learning framework, and the distinguished feature of FL is that the clients involved in training do not need to share raw data, but only transfer the model parameters to share knowledge, and finally get a global model with improved performance. However, recent studies have found that sharing model parameters may still lead to privacy leakage. From the shared model parameters, local training data can be reconstructed and thus lead to a threat to individual privacy and security. We observed that most of the current attacks are aimed at client-specific data reconstruction, while limited attention is paid to the information leakage of the global model. In our work, we propose a novel FL attack based on shared model parameters that can deduce the data distribution of the global model. Different from other FL attacks that aim to infer individual clients’ raw data, the data distribution inference attack proposed in this work shows that the attackers can have the capability to deduce the data distribution information behind the global model. We argue that such information is valuable since the training data behind a well-trained global model indicates the common knowledge of a specific task, such as social networks and e-commerce applications. To implement such an attack, our key idea is to adopt a deep reinforcement learning approach to guide the attack process, where the RL agent adjusts the pseudo-data distribution automatically until it is similar to the ground truth data distribution. By a carefully designed MDP process, our implementation ensures our attack can have stable performance and experimental results verify the effectiveness of our proposed inference attack.

A hypergraph is a mathematical structure capable of representing complex relationships among multiple entities, with widespread applications. However, as the size of hypergraphs continues to grow, their analysis and processing become increasingly challenging. Therefore, how to effectively process large hypergraphs to enable efficient analysis with limited computational resources has become an important research problem. In this article, we propose a method called hypergraph adaptive sampling (HAS), a framework that achieves adaptive batch sampling of hyperedges. This framework adaptively adjusts the sampling probability of hyperedges to ensure that the sampled subhypergraph closely resembles the original hypergraph in terms of structural characteristics, effectively reducing information loss caused by sampling. Extensive experiments are conducted on six public datasets to evaluate, and the results demonstrate that HAS outperforms other algorithms in preserving hypergraph properties. Using our hypergraph sampling method, even when only 20% of the edges of the original image are sampled, the sampled subhypergraph still maintains a small structural error compared to the original hypergraph. The KL divergence of the subhypergraph degree distribution is 0.09, which is 4.1${\boldsymbol\times}$better than the baseline. Last, the efficiency and adaptability of HAS make it applicable not only to hypergraph analysis but also for providing a general and scalable solution for efficiently processing large-scale hypergraph data.

Graph unlearning aims to provably remove some training data from graph neural networks (GNNs) while eliminating their impact on model predictions. Although retraining the GNNs from scratch is a direct and legitimate solution, it entails substantial computational resources. To address this issue, graph unlearning methods have been proposed in the domain of graph data. However, applying existing graph unlearning methods directly to hypergraph data affects model utility. Specifically, the graph unlearning methods severely damage the higher-order structural information of hypergraphs and fail to remove all the information that needs to be unlearned. In this paper, we propose Hyperedge Size-Based Core-Sharing Decomposition, a novel hypergraph unlearning framework tailored to the structural characteristics of hypergraph data. Its contributions include a subgraph partitioning method specific to hypergraphs and an aggregation method based on node coverage. We conduct extensive experiments on seven real-world hypergraph datasets to demonstrate the unlearning efficiency and model utility. Compared to the baseline methods, our approach achieves up to 5% higher accuracy and reduces the average unlearning time by 28%. Furthermore, our node-coverage-based aggregation approach achieves up to 6% higher accuracy.

To address the online learning problem in distributed systems, Streaming Federated learning (SFL) enables immediate model training by clients upon collecting new data, finding wide applications in AI-enabled Internet-of-Things and sensor networks. Given the variability in data distribution across different historical periods, the ability to recall and rapidly apply previously encountered data distributions significantly enhances the efficiency and accuracy of model training. In this paper, a demo based on the real-world temperature datasets is presented to demonstrate the importance of history knowledge in local training and the federating process of SFL, which also shows that vanilla federated learning without considering the history knowledge may even be harmful to model training. Observing this, we propose Fed-HIST, a Federated learning framework that enables the clients to learn from the HISTory knowledge of the whole distributed learning system. Unlike direct raw data storage, Fed-HIST employs model architectures to capture the data distributions, offering a more space-efficient and privacy-preserving method of knowledge storage on a server pool. Additionally, a model similarity comparison scheme is designed to retrieve beneficial knowledge from the pool uploaded by the clients in the past. Such a history-aware federation can enhance the efficiency of training each client, only requiring the recurrence of similar data distributions among SFL participants. We validate our framework through extensive simulations on MNIST, Fashion-MINST, CIFAR10, and CIFAR100 datasets, benchmarking against 9 baselines and highlighting the importance of federating from history in SFL problem through necessary ablation studies.

Wireless networks have become integral to modern communication systems, enabling the seamless exchange of information across a myriad of applications. However, the inherent characteristics of wireless channels, such as fading, interference, and openness, pose significant challenges to achieving fault-tolerant consensus within these networks. Fault-tolerant consensus, a critical aspect of distributed systems, ensures that network nodes collectively agree on a consistent value even in the presence of faulty or compromised components. This survey paper provides a comprehensive overview of fault-tolerant consensus mechanisms specifically tailored for wireless networks. We explore the diverse range of consensus protocols and techniques that have been developed to address the unique challenges of wireless environments. The paper systematically categorizes these consensus mechanisms based on their underlying principles, communication models, and fault models. It investigates how these mechanisms handle various types of faults, including communication errors, node failures, and malicious attacks. It highlights key use cases, such as sensor networks, Internet of Things applications, wireless blockchain, and vehicular networks, where fault-tolerant consensus plays a pivotal role in ensuring reliable and accurate data dissemination.

The distinct attributes of Internet of Things (IoTs) devices, including the disparity between training and testing data distributions and limited availability of training data, pose challenges for deep learning models in effectively addressing unseen domain segmentation tasks. Federated Learning (FL) can increase the participation of various data contributors, thus has great potential to develop a unified framework to shed light on the relationship between unseen domains and generalized domains. In this paper, we proposed an FL-based unseen domain segmentation model. The architecture includes (1) an external memory module as an object feature guide to reduce the feature ambiguity of unseen domain objects. (2) A re-attention activation mechanism for better completing localization of unseen domain objects, enhancing the features of potential targets and suppressing interference features. (3) A self-supervised learning paradigm for achieving specific object feature exploration. Based on flexible splitting and combining, our model is able to capture both personalization and generalization capabilities, the client side retains a strong personalization ability, while the server side has a strong generalization ability. Moreover, taking into account the inherent limitations in computing and storage resources commonly associated with IoT devices, the introduced model leverages the concept of optional dependencies to enable efficient inference within resource-constrained client environments. Our proposed model is validated through extensive experiments. The approach proposed in this paper outperforms the generalization capabilities of state-of-the-art work on several benchmarks.

Federated Learning (FL) offers collaborative machine learning without data exposure, but challenges arise in the mobile edge network (MEC) environment due to limited resources and dynamic conditions. This paper presents a Digital Twin (DT)-assisted FL platform for MEC networks and introduces a novel multi-FL service framework to address resource dynamics and mobile users. We leverage DT models to optimize device scheduling and MEC resource allocation, aiming to maximize utility across FL services. Our work includes heuristic and constant approximation algorithms for offline multi-FL service scenarios and we also investigate an online setting of our solution with dynamic bandwidth and moving client conditions. To adapt to changing network conditions, we utilize historical bandwidth data in DTs and implement a deep reinforcement learning algorithm, Ra_DDPG, for automatic bandwidth allocation. Evaluation results demonstrate a significant 49.8% increase in system utility compared to a benchmark algorithm, showcasing the effectiveness of our approach.

Edge intelligence is an emerging technology that enables artificial intelligence on connected systems and devices in close proximity to the data sources. Decentralized Collaborative Learning (DCL) is a novel edge intelligence technique that allows distributed clients to cooperatively train a global learning model without revealing their data. DCL has a wide range of applications in various domains, such as smart city and autonomous driving. However, DCL faces significant challenges in ensuring its trustworthiness, as data isolation and privacy issues make DCL systems vulnerable to adversarial attacks that aim to breach system confidentiality, undermine learning reliability or violate data privacy. Therefore, it is crucial to design DCL in a trustworthy manner, with a focus on security, robustness, and privacy. In this survey, we present a comprehensive review of existing efforts for designing trustworthy DCL systems from the three key aformentioned aspects: security, robustness, and privacy. We analyze the threats that affect the trustworthiness of DCL across different scenarios and assess specific technical solutions for achieving each aspect of Trustworthy DCL (TDCL). Finally, we highlight open challenges and future directions for advancing TDCL research and practice.

The study of graph kernels has been an important area of graph analysis, which is widely used to solve the similarity problems between graphs. Most of the existing graph kernels consider either local or global properties of the graph, and there are few studies on multiscale graph kernels. In this article, the authors propose a framework for graph kernels based on truss decomposition, which allows multiple graph kernels and even any graph comparison algorithms to compare graphs at different scales. The authors utilize this framework to derive variants of five graph kernels and compare them with the corresponding basic graph kernels on graph classification tasks. Experiments on a large number of benchmark datasets demonstrate the effectiveness and efficiency of the proposed framework.

Today's business environment is characterized by uncertainty and competition, so the capability to adapt to the evolving era and unforeseen challenges is essential in business strategies. Recent studies on extended enterprise indicate that collaboration among different stakeholders is beneficial for surviving these unexpected changes. However, the barriers such as market uncertainty, privacy and trust concerns, and individual contribution evaluation limit the implementation and application of the extended enterprise concept. Federated learning (FL), in which multiple enterprise entities can use a shared model while retaining all training data locally, has emerged as a promising artificial intelligence (AI) solution for accumulating insights from multiple stakeholders and providing collaborative decision-making. Furthermore, the enhanced privacy-protection benefits of FL remove the barriers to implementing extended enterprise collaboration. In particular, an FL central server manages the local updates of multiple enterprise entities (FL clients) and aggregates their contributions to improve the global model training. Meanwhile, to address the time-series graph learning problem in most business environments, we incorporate temporal convolutional network, graph convolutional neural network, and gated recurrent unit architecture into FL to capture the temporal-spatial dependencies in individual data sources. Furthermore, we use traffic flow forecasting as the use case of our proposed framework to verify its effectiveness. Finally, the experimental results on a real traffic flow dataset and the comparison results with the state-of-the-art baseline methods show that our proposed solution achieves superior performance.

More and more applications are promoting cus-tomized or personalized services. In order for these applications to provide meaningful output, it collects users’ personal information over time. Some personal information (e.g. education level or income level) can only be captured by users actively updating their profile to reflect these changes. We refer to these as long-term time series data, as they do not change frequently. If applications can keep up to date on a diverse and large set of personal features, they can provide higher quality service. However, this quality of service comes at the cost of the user sacrificing their privacy. There has been numerous research on protecting privacy of time series data for context aware services, but the privacy leakage of personal information updates during the whole life-cycle of the series has received only scant attention.Motivated users concerned about their privacy, we discuss in detail the privacy leakage risk, focusing on long-term time-series data from the perspective of game theory. Then, we propose a reward-privacy model, targeting the privacy-aware data-updates for the entire life-cycle in context-aware services by leveraging a three-party Stackelberg game. We theoretically prove that a Nash Equilibrium exists in the proposed model, and then use simulations to validate that a Nash Equilibrium exists for different parameters of the productivity function. By using our proposed framework, users have guidance to decide not only the timing of submitting personal updates, but also the granularity or obscurity level for their data.

The ubiquity of devices in Internet of Things (IoT) has opened up a large source for IoT data. Machine learning (ML) models with big IoT data is beneficial to our daily life in monitoring air condition, pollution, climate change, etc. However, centralized conventional ML models rely on all clients' data at a central server, which seriously threatens user privacy. Federated learning (FL) emerges as a promising solution aiming to protect user privacy by enabling model training on a large corpus of decentralized data. The recent studies indicate FL suffers from the heterogeneity issue as it treats all clients' data equally, that is, FL might sacrifice the performance of the majority of clients to accommodate the performance of the minority of clients with low usability data. In order to overcome this issue, a reinforcement learning (RL)-based intelligent central server with the capability of recognizing heterogeneity is implemented, which can help lead the trend toward better performance for majority of clients. To be specific, an FL central server analyses the benefits of different collaboration by capturing the intricate patterns in heterogeneous clients based on rating feedback and then updates clients' weights iteratively, until it establishes a coalition of clients with quasioptimal performance. The experimental results on three real data sets under various heterogeneity levels demonstrate the superior performance of the proposed solution.

The IoT era observes the increasing demand for data to support various applications and services. The Mobile Crowdsensing (MCS) system then emerged. By utilizing the hybrid intelligence of humans and sensors, it is significantly beneficial to keep collecting high‐quality sensing data for all kinds of IoT applications, such as environmental monitoring, intelligent healthcare services, and traffic management. However, the service quality of MCS systems relies on a dedicated designed task allocation framework, which needs to consider the participant resource bottleneck and system utility at the same time. Recent studies tend to use a different solution to solve the two challenges. The incentive mechanism is for resolving the participant shortage problem, and task assignment methods are studied to find the best match of participants and system utility goal of MCS. Thus, existing task allocation frameworks fail to consider the participant’s expectations deeply. We propose a semiopportunistic concept‐based solution to overcome this issue. Similar to the “shared mobility” concept, our proposed task allocation framework can offer the participants routing advice without disturbing their original travel plan. The participant can accomplish the sensing request on his route. We further consider the system constraints to determine a subgroup of participants that can obtain the utility optimization goal. Specifically, we use the Graph Attention Network (GAT) to produce the target sensing area’s virtual representation and provide the participant with a payoff‐maximized route. Such a method makes our solution adapt to most of MCS scenarios’ conditions instead of using fixed system settings. Then, a reinforcement learning‐ (RL‐) based task assignment is adopted, which can help the MCS system towards better performance improvements while support different utility functions. The simulation results on various conditions demonstrate the superior performance of the proposed solution.